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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 40197
    Prev
    Next
    INDEX
    Explanations

    mentions of events, announcements, and specific dates

    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
    •Layer 6 UMAP region: Mixed cluster on right - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.23
    1.0%
    393
    +0.13
    0.6%
    526
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.23
    0.12
    362
    +0.13
    0.12
    589
    +0.11
    0.09
    Negative Logits
    cro
    -0.75
    gans
    -0.74
    bestos
    -0.72
    ctor
    -0.70
    stead
    -0.69
    aceutical
    -0.69
     benefited
    -0.68
    Connector
    -0.67
    ships
    -0.67
    adoes
    -0.67
    POSITIVE LOGITS
     least
    1.26
     halftime
    1.03
    yp
    0.94
    mosp
    0.90
    onement
    0.89
    las
    0.89
     dusk
    0.87
     Cannes
    0.86
     conferences
    0.85
     CES
    0.85
    Activations Density 8.320%

    No Known Activations