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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 43415
    Prev
    Next
    INDEX
    Explanations

    instances of the word "against."

    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
    305
    +0.09
    0.4%
    430
    +0.09
    0.4%
    238
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    305
    +0.09
    0.02
    238
    +0.09
    0.02
    603
    +0.09
    0.02
    Negative Logits
    pmwiki
    -0.98
    cffff
    -0.85
    iscal
    -0.80
    DragonMagazine
    -0.77
    verified
    -0.77
    erred
    -0.76
    aund
    -0.76
    argon
    -0.75
    udder
    -0.74
    rared
    -0.73
    POSITIVE LOGITS
     Notre
    0.94
     Samoa
    0.89
     opponents
    0.84
     opponent
    0.83
     Serbia
    0.81
     Nicaragua
    0.81
     Tampa
    0.80
     Minnesota
    0.79
     Carolina
    0.79
     Slovakia
    0.79
    Activations Density 0.017%

    No Known Activations