© 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 49152
    9. 8-RES_FS49152-JB
    11. 37452
    Prev
    Next
    INDEX
    Explanations

    sentences indicating completion or closure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.17
    0.8%
    430
    +0.14
    0.7%
    447
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.17
    0.10
    679
    +0.14
    0.09
    640
    +0.14
    0.08
    Negative Logits
     tack
    -0.78
     graz
    -0.71
     submerged
    -0.71
     fung
    -0.70
    unts
    -0.69
     clipped
    -0.68
    affer
    -0.67
    antz
    -0.66
     temperament
    -0.66
     perspect
    -0.65
    POSITIVE LOGITS
     Congratulations
    1.32
     Firstly
    1.13
     Please
    1.12
     Whilst
    1.11
     Hopefully
    1.08
     Yesterday
    1.08
     Located
    0.99
     ðŁĻĤ
    0.99
     Its
    0.98
     Prepare
    0.97
    Activations Density 0.323%

    No Known Activations