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. 13621
    Prev
    Next
    INDEX
    Explanations

    information related to legal cases or government actions with some negative context

    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
    +0.32
    1.8%
    393
    +0.10
    0.6%
    73
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.32
    0.37
    640
    +0.10
    0.35
    721
    +0.07
    0.14
    Negative Logits
    uci
    -0.56
    igmatic
    -0.56
    angu
    -0.54
    sburg
    -0.53
    agall
    -0.51
    iors
    -0.50
    grain
    -0.49
     Deity
    -0.49
    Switch
    -0.49
    paren
    -0.48
    POSITIVE LOGITS
     however
    0.85
     billed
    0.65
     dubbed
    0.65
     moreover
    0.64
     namely
    0.62
     comprising
    0.62
     incidentally
    0.60
     according
    0.59
     albeit
    0.59
     titled
    0.59
    Activations Density 19.332%

    No Known Activations