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. 23831
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and the concept of responsibility

    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
    393
    +0.17
    0.8%
    395
    +0.11
    0.5%
    74
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.17
    0.05
    362
    +0.11
    0.05
    384
    +0.11
    0.02
    Negative Logits
    Loading
    -0.79
    Dynamic
    -0.78
    Inter
    -0.75
    Accept
    -0.73
    ©¶æ¥µ
    -0.72
    nit
    -0.72
    Lost
    -0.71
    Ub
    -0.71
    iably
    -0.71
    Nit
    -0.71
    POSITIVE LOGITS
     person
    1.14
     guy
    1.02
     woman
    0.94
     town
    0.93
     girl
    0.89
     country
    0.87
     house
    0.86
     man
    0.85
     plane
    0.84
     seller
    0.84
    Activations Density 0.212%

    No Known Activations