© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 26801
    Prev
    Next
    INDEX
    Explanations

    phrases and terms associated with groups, categorization, and classifications

    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
    481
    +0.27
    1.3%
    717
    +0.09
    0.4%
    643
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    732
    +0.27
    0.03
    79
    +0.09
    0.04
    88
    +0.09
    0.03
    Negative Logits
     Rosenstein
    -0.83
    ãĥ¼ãĥ³
    -0.74
    iverse
    -0.72
    soType
    -0.72
     Luxem
    -0.70
     Franch
    -0.69
    orthy
    -0.68
    uably
    -0.68
     Majority
    -0.67
     Liberties
    -0.67
    POSITIVE LOGITS
     digging
    1.10
     drilling
    1.08
     surfing
    1.08
     drills
    1.05
     spraying
    1.05
     hiking
    1.04
     bathing
    1.04
     brushing
    1.04
     harvesting
    1.04
     chewing
    1.02
    Activations Density 0.273%

    No Known Activations