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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 43470
    Prev
    Next
    INDEX
    Explanations

    phrases related to origins or causes of issues

    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
    759
    +0.11
    0.5%
    171
    +0.11
    0.5%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    252
    +0.11
    0.04
    569
    +0.11
    0.04
    195
    +0.10
    0.02
    Negative Logits
    taker
    -0.63
    mouth
    -0.63
    dogs
    -0.62
     pads
    -0.59
     bowls
    -0.59
     monitors
    -0.58
     Breaker
    -0.57
    /-
    -0.57
     tumble
    -0.57
     thumbs
    -0.56
    POSITIVE LOGITS
     partly
    0.96
     rooted
    0.86
     unden
    0.83
     chiefly
    0.83
     stems
    0.78
     principally
    0.77
     traced
    0.77
     manifold
    0.76
    tymology
    0.75
     origins
    0.75
    Activations Density 0.191%

    No Known Activations