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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 26085
    Prev
    Next
    INDEX
    Explanations

    mentions of film release dates and related promotional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    579
    +0.11
    0.5%
    373
    +0.10
    0.5%
    460
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.11
    0.03
    198
    +0.10
    0.03
    310
    +0.10
    0.03
    Negative Logits
    acan
    -0.73
    ¬¼
    -0.70
    notation
    -0.68
    anca
    -0.68
    efe
    -0.68
     clipboard
    -0.65
    ¯
    -0.64
    pmwiki
    -0.63
    rians
    -0.63
    olated
    -0.62
    POSITIVE LOGITS
     Thurs
    1.03
     Fridays
    0.94
     Tues
    0.94
     Mondays
    0.93
     premie
    0.92
     paperback
    0.90
     airs
    0.87
     Dynam
    0.84
     theaters
    0.81
     priced
    0.81
    Activations Density 0.196%

    No Known Activations