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 24576
    5. 8-RES_FS24576-JB
    6. 869
    Prev
    Next
    INDEX
    Explanations

    mentions of personal experiences or inner struggles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    608
    +0.10
    0.4%
    373
    +0.09
    0.4%
    456
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    696
    +0.10
    0.05
    428
    +0.09
    0.04
    431
    +0.09
    0.04
    Negative Logits
     protected
    -0.74
     DRAGON
    -0.68
     circ
    -0.65
    manship
    -0.63
     retirees
    -0.63
     populated
    -0.60
     disabled
    -0.60
     guided
    -0.59
     Herm
    -0.58
     couch
    -0.57
    POSITIVE LOGITS
    't
    1.47
    ÃŃ
    1.05
    ned
    0.92
    nt
    0.91
    itive
    0.91
    iting
    0.91
    etsk
    0.90
    NT
    0.89
    kered
    0.89
    ge
    0.86
    Activations Density 0.064%

    No Known Activations