© 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 24576
    9. 8-RES_FS24576-JB
    11. 8504
    Prev
    Next
    INDEX
    Explanations

    references to specific or proper nouns

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    356
    +0.09
    0.4%
    386
    +0.09
    0.4%
    497
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.09
    0.02
    632
    +0.09
    0.01
    308
    +0.08
    0.01
    Negative Logits
    İĭ
    -0.72
    kie
    -0.68
     plateau
    -0.66
    ality
    -0.62
     sack
    -0.60
    aido
    -0.59
     hust
    -0.59
    ists
    -0.59
     lawn
    -0.57
    lance
    -0.57
    POSITIVE LOGITS
    LOG
    0.80
    EMOTE
    0.80
    76561
    0.77
    SAY
    0.71
    Computer
    0.71
    GAME
    0.71
     Transcript
    0.70
    Console
    0.70
    Ep
    0.70
    liquid
    0.69
    Activations Density 0.023%

    No Known Activations