© 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 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. 12511
    Prev
    Next
    INDEX
    Explanations

    information related to online resources and 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
    640
    +0.21
    1.0%
    314
    +0.14
    0.7%
    107
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.21
    0.04
    648
    +0.14
    0.03
    313
    +0.13
    0.03
    Negative Logits
     creep
    -0.72
     pores
    -0.71
     creeping
    -0.70
     faintly
    -0.69
     soaring
    -0.68
     overtime
    -0.68
     patrolling
    -0.68
     hugged
    -0.67
     receiving
    -0.67
     outsiders
    -0.67
    POSITIVE LOGITS
    detail
    1.57
    index
    1.49
    pmwiki
    1.37
    english
    1.36
    wp
    1.35
    archives
    1.34
    articles
    1.30
    features
    1.26
    topic
    1.23
    uploads
    1.23
    Activations Density 0.040%

    No Known Activations