© 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. 8712
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    285
    +0.12
    0.6%
    232
    +0.09
    0.4%
    613
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.12
    0.05
    6
    +0.09
    0.05
    166
    +0.09
    0.04
    Negative Logits
     corrid
    -0.70
     swamp
    -0.68
     inclusive
    -0.66
     portal
    -0.65
    apan
    -0.65
    oute
    -0.65
    stem
    -0.64
    aper
    -0.64
     docking
    -0.63
     binge
    -0.63
    POSITIVE LOGITS
     Nope
    1.50
     Absolutely
    1.36
     Probably
    1.36
     Possibly
    1.33
     Certainly
    1.32
     Maybe
    1.18
     Yes
    1.18
     Surely
    1.16
     Hmm
    1.16
     Perhaps
    1.14
    Activations Density 0.071%

    No Known Activations