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. 23894
    Prev
    Next
    INDEX
    Explanations

    elements related to visual content and media

    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
    373
    +0.12
    0.6%
    37
    +0.09
    0.4%
    398
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.00
    398
    +0.09
    0.01
    268
    +0.09
    0.01
    Negative Logits
    ĵĺ
    -0.74
     league
    -0.68
    ©¶æ¥µ
    -0.68
    gate
    -0.68
    SPONSORED
    -0.67
    shaw
    -0.63
    beh
    -0.60
     creeps
    -0.60
    omsky
    -0.60
    tsy
    -0.59
    POSITIVE LOGITS
     Participants
    0.77
     Protesters
    0.69
     Examples
    0.68
     Dozens
    0.67
     Scenes
    0.65
     Hundreds
    0.65
     Residents
    0.64
     Thousands
    0.63
    obyl
    0.61
     Prot
    0.60
    Activations Density 0.004%

    No Known Activations