© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13431
    Prev
    Next
    INDEX
    Explanations

    mentions of someone or something entering or being entered into agreements or events

    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
    13
    +0.10
    0.5%
    569
    +0.10
    0.4%
    299
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.10
    0.03
    469
    +0.10
    0.02
    569
    +0.10
    0.02
    Negative Logits
    fml
    -0.63
    killer
    -0.61
     Archangel
    -0.59
    bara
    -0.58
    gnu
    -0.58
    ector
    -0.57
     backdrop
    -0.57
    cks
    -0.57
    iane
    -0.56
    die
    -0.56
    POSITIVE LOGITS
    prising
    1.45
    prise
    1.20
    prises
    1.19
    tain
    1.05
    TAIN
    1.05
    tainment
    1.02
     into
    0.94
     INTO
    0.94
    taining
    0.89
    tained
    0.88
    Activations Density 0.033%

    No Known Activations