© 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. 18431
    Prev
    Next
    INDEX
    Explanations

    descriptions of encounters with mysterious or fantastical entities

    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
    237
    +0.09
    0.4%
    419
    +0.09
    0.4%
    467
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.09
    0.06
    326
    +0.09
    0.06
    35
    +0.09
    0.04
    Negative Logits
    umbn
    -0.88
    ilater
    -0.76
     Replacement
    -0.71
    Box
    -0.70
     Box
    -0.69
    ENTION
    -0.68
     attribution
    -0.66
    Problem
    -0.65
    Sources
    -0.65
     taxpayer
    -0.64
    POSITIVE LOGITS
     shimmer
    1.20
     crimson
    1.13
     throb
    1.11
     gle
    1.02
     faintly
    0.99
     translucent
    0.99
     breeze
    0.98
     sparkling
    0.97
     haze
    0.95
     illuminating
    0.95
    Activations Density 0.388%

    No Known Activations