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. 40140
    Prev
    Next
    INDEX
    Explanations

    details related to film production and direction

    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
    592
    +0.14
    0.6%
    447
    +0.11
    0.5%
    473
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.14
    0.09
    725
    +0.11
    0.07
    360
    +0.09
    0.09
    Negative Logits
    bos
    -0.73
     deductible
    -0.71
    imaru
    -0.71
    osi
    -0.70
    tro
    -0.66
    alore
    -0.65
     ultras
    -0.65
    rir
    -0.63
     freezer
    -0.62
    onew
    -0.61
    POSITIVE LOGITS
    writer
    0.84
     studio
    0.83
    RECT
    0.81
     screenplay
    0.80
    itled
    0.78
    writing
    0.73
    writers
    0.73
    isodes
    0.72
    director
    0.72
    ducers
    0.70
    Activations Density 8.151%

    No Known Activations