© 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. 18618
    Prev
    Next
    INDEX
    Explanations

    words related to self-inflicted actions or conditions

    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
    708
    +0.10
    0.5%
    454
    +0.10
    0.5%
    302
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    708
    +0.10
    0.02
    248
    +0.10
    0.02
    555
    +0.10
    0.02
    Negative Logits
    sea
    -0.83
    estone
    -0.76
    endez
    -0.71
    ugu
    -0.68
    KEY
    -0.68
    eday
    -0.67
     Collider
    -0.66
    anwhile
    -0.64
    swick
    -0.64
    staff
    -0.63
    POSITIVE LOGITS
    itled
    0.72
     attribution
    0.69
    essed
    0.66
    rency
    0.65
     prophecy
    0.65
    rating
    0.65
    destruct
    0.64
    rifice
    0.64
    iency
    0.63
     gratification
    0.63
    Activations Density 0.054%

    No Known Activations