© 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. 45738
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate proximity or presence, particularly the word "around."

    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
    253
    +0.10
    0.4%
    687
    +0.10
    0.4%
    578
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.10
    0.02
    422
    +0.10
    0.01
    125
    +0.10
    0.01
    Negative Logits
    eln
    -0.71
    ãĤº
    -0.70
    BT
    -0.70
    ascript
    -0.69
    xual
    -0.69
    deal
    -0.68
    ELS
    -0.66
    é¾į
    -0.65
    enburg
    -0.65
    oise
    -0.64
    POSITIVE LOGITS
     corners
    0.84
     town
    0.72
     awhile
    0.70
     here
    0.69
    abouts
    0.66
    clock
    0.65
     anymore
    0.63
     quieter
    0.61
    perty
    0.61
     tremend
    0.60
    Activations Density 0.019%

    No Known Activations