© 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. 6675
    Prev
    Next
    INDEX
    Explanations

    terms related to agriculture, politics, and society

    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
    481
    +0.22
    1.0%
    51
    +0.11
    0.5%
    762
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.08
    423
    +0.11
    0.07
    481
    +0.10
    0.07
    Negative Logits
    escription
    -0.69
    inyl
    -0.63
    iago
    -0.63
    POR
    -0.62
    orph
    -0.61
    urat
    -0.60
    illin
    -0.59
     Kraft
    -0.59
     Zup
    -0.58
    iban
    -0.58
    POSITIVE LOGITS
     exacerbated
    0.77
     sphere
    0.74
     periphery
    0.74
     contexts
    0.72
    .}
    0.71
    ament
    0.70
     caused
    0.70
    .
    0.70
     context
    0.69
     despite
    0.68
    Activations Density 0.422%

    No Known Activations