© 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. 9688
    Prev
    Next
    INDEX
    Explanations

    references to copyright disclaimers or legal information at the end of documents

    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
    +0.18
    0.9%
    373
    +0.16
    0.8%
    706
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.18
    0.06
    373
    +0.16
    -0.01
    70
    +0.09
    0.04
    Negative Logits
     cit
    -0.68
     Dyn
    -0.65
     Hamm
    -0.64
     Tomb
    -0.63
     Clo
    -0.61
     Iron
    -0.60
     Cyborg
    -0.59
     Squadron
    -0.59
     IGF
    -0.59
     Tide
    -0.57
    POSITIVE LOGITS
    pmwiki
    0.81
    SHARE
    0.77
    rawdownloadcloneembedreportprint
    0.76
    verett
    0.76
    ampa
    0.75
    ccording
    0.74
    MI
    0.72
    Fair
    0.71
    ³³³³³³³³
    0.71
    Posted
    0.70
    Activations Density 0.094%

    No Known Activations