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. 13550
    Prev
    Next
    INDEX
    Explanations

    comparisons between different entities or concepts

    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
    +0.30
    1.4%
    393
    +0.13
    0.6%
    88
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.30
    0.35
    448
    +0.13
    0.09
    14
    +0.10
    0.09
    Negative Logits
    Accessory
    -0.72
    lied
    -0.68
     veter
    -0.67
     Takeru
    -0.64
    nown
    -0.64
    acia
    -0.64
    overed
    -0.62
    iona
    -0.62
    aced
    -0.60
    urther
    -0.59
    POSITIVE LOGITS
     ours
    0.66
     those
    0.62
     outright
    0.59
     namely
    0.59
    aqu
    0.58
    stellar
    0.58
     visually
    0.57
    ascript
    0.56
    mbuds
    0.56
     hers
    0.56
    Activations Density 12.893%

    No Known Activations