© 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. 12132
    Prev
    Next
    INDEX
    Explanations

    imperative verbs directed towards involvement or action

    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
    608
    +0.10
    0.4%
    184
    +0.09
    0.4%
    49
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.10
    0.02
    184
    +0.09
    0.01
    551
    +0.09
    0.02
    Negative Logits
    ELD
    -0.76
    ãĤ¦ãĤ¹
    -0.69
    quickShipAvailable
    -0.69
    MpServer
    -0.68
    pires
    -0.65
     impossibility
    -0.65
     Fundamental
    -0.64
    adra
    -0.64
     Reconstruction
    -0.63
     delusions
    -0.62
    POSITIVE LOGITS
     check
    1.14
     subscribe
    1.10
     revisit
    1.04
     indulge
    0.99
     donate
    0.98
     leave
    0.97
     nominate
    0.97
     mention
    0.97
     visit
    0.97
     submit
    0.96
    Activations Density 0.043%

    No Known Activations