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 3072
    5. 8-RES_FS3072-JB
    6. 2093
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotion or opinion

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    481
    +0.18
    0.8%
    156
    +0.10
    0.4%
    533
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.18
    0.12
    557
    +0.10
    0.07
    362
    +0.09
    0.09
    Negative Logits
    utical
    -0.75
    aceae
    -0.73
    MX
    -0.72
    ngth
    -0.71
    è£
    -0.70
    igmatic
    -0.69
    isSpecialOrderable
    -0.68
    ourage
    -0.68
    ãģ®éŃĶ
    -0.67
    uum
    -0.67
    POSITIVE LOGITS
     hearing
    0.93
     seeing
    0.92
     inaction
    0.92
     losing
    0.88
     perceived
    0.86
     witnessing
    0.85
     sudden
    0.83
     suggestions
    0.82
     injustice
    0.81
     allegations
    0.80
    Activations Density 1.667%

    No Known Activations