© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 26754
    Prev
    Next
    INDEX
    Explanations

    phrases that involve signs or statements made by individuals or groups

    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
    59
    +0.12
    0.5%
    430
    +0.09
    0.4%
    252
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.12
    0.02
    725
    +0.09
    0.02
    59
    +0.09
    0.02
    Negative Logits
    asions
    -0.78
    uries
    -0.70
    lance
    -0.69
    enario
    -0.69
    aughs
    -0.69
    uristic
    -0.69
    folio
    -0.69
    erker
    -0.67
    ucket
    -0.67
    imester
    -0.66
    POSITIVE LOGITS
     "#
    1.02
     logos
    0.82
     Amen
    0.80
     inscribed
    0.79
     "+
    0.72
    plates
    0.71
     "$
    0.70
     illuminated
    0.69
     Supports
    0.69
     ""
    0.68
    Activations Density 0.074%

    No Known Activations