Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34578
    Prev
    Next
    INDEX
    Explanations

    paragraphs related to economic policies, investments, and financial regulations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.33
    1.8%
    640
    +0.28
    1.5%
    481
    +0.18
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.33
    0.36
    442
    +0.28
    0.19
    160
    +0.18
    0.26
    Negative Logits
     submar
    -0.62
     frontline
    -0.61
     McMaster
    -0.60
     consulate
    -0.60
    ensical
    -0.59
    ĸļ
    -0.59
     suff
    -0.58
     escal
    -0.58
     reneg
    -0.58
     ridic
    -0.57
    POSITIVE LOGITS
    --------------------------------------------------------
    1.32
    Advertisements
    1.23
    ________________________________________________________________
    1.13
    ----------------------------------------------------------------
    1.11
    --------------------
    1.10
    ======
    1.05
    ------------------------------------------------
    1.05
    ________________________
    1.05
    ============
    1.05
    Conclusion
    1.04
    Activations Density 9.518%

    No Known Activations