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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 40298
    Prev
    Next
    INDEX
    Explanations

    keywords related to business and financial information

    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
    87
    +0.43
    3.1%
    266
    +0.27
    2.0%
    447
    +0.21
    1.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.43
    -0.01
    266
    +0.27
    0.68
    64
    +0.21
    -0.58
    Negative Logits
    pmwiki
    -0.46
     Sno
    -0.39
    ograp
    -0.38
     âĢİ
    -0.37
    WHERE
    -0.37
    atform
    -0.36
    eatures
    -0.36
     iP
    -0.36
    Apps
    -0.34
    bard
    -0.34
    POSITIVE LOGITS
    ghazi
    0.43
     courier
    0.33
    pload
    0.33
    fu
    0.32
    partisan
    0.32
     partisans
    0.32
     UAE
    0.31
     depot
    0.31
     stroke
    0.31
     Kaine
    0.31
    Activations Density 51.705%

    No Known Activations