© 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 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. 6498
    Prev
    Next
    INDEX
    Explanations

    informal, conversational phrases expressing personal opinions or preferences

    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
    735
    +0.11
    0.5%
    757
    +0.10
    0.5%
    718
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    757
    +0.11
    0.03
    735
    +0.10
    0.03
    718
    +0.10
    0.04
    Negative Logits
    ahime
    -0.87
    aye
    -0.82
    dm
    -0.79
    externalActionCode
    -0.79
    alf
    -0.77
    AAF
    -0.75
    yet
    -0.72
    folios
    -0.70
    DF
    -0.69
    iants
    -0.69
    POSITIVE LOGITS
    theless
    0.91
     lurking
    0.89
    entimes
    0.85
     dreamed
    0.83
     strive
    0.78
     underestimated
    0.76
     striving
    0.75
     fascinated
    0.75
     evolving
    0.75
     bothered
    0.74
    Activations Density 0.042%

    No Known Activations