© 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. 20756
    Prev
    Next
    INDEX
    Explanations

    discussion related to video games and community interactions

    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
    393
    +0.10
    0.4%
    738
    +0.09
    0.4%
    52
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.10
    0.06
    0
    +0.09
    0.06
    351
    +0.08
    0.05
    Negative Logits
    utenberg
    -0.78
    Contents
    -0.75
    dayName
    -0.75
    ANC
    -0.73
     Corpus
    -0.70
    particularly
    -0.68
    Enhanced
    -0.68
    ajor
    -0.66
    CLASSIFIED
    -0.65
    YD
    -0.64
    POSITIVE LOGITS
     THEN
    1.34
     then
    1.27
     suddenly
    1.12
     magically
    1.02
     thereby
    0.98
     reap
    0.93
     pretend
    0.90
     prest
    0.89
     forget
    0.88
     somehow
    0.88
    Activations Density 0.284%

    No Known Activations