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. 13552
    Prev
    Next
    INDEX
    Explanations

    references to video games and fictional characters with superhero-like or fantastical elements

    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
    404
    +0.11
    0.5%
    240
    +0.10
    0.4%
    153
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.11
    0.08
    97
    +0.10
    0.05
    611
    +0.09
    0.13
    Negative Logits
    ashtra
    -0.93
    »Ĵ
    -0.88
    uscript
    -0.71
    marg
    -0.71
    acca
    -0.70
    auga
    -0.70
    etheless
    -0.67
    iland
    -0.67
    ĻĤ
    -0.67
    cdn
    -0.66
    POSITIVE LOGITS
     Duty
    0.75
     Cube
    0.70
    Vision
    0.65
     arms
    0.65
    izard
    0.62
     Cthulhu
    0.61
     wake
    0.60
     Ju
    0.60
     Conquer
    0.60
     Ware
    0.60
    Activations Density 10.910%

    No Known Activations