© 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. 18545
    Prev
    Next
    INDEX
    Explanations

    names of individuals in a list

    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
    99
    +0.11
    0.5%
    357
    +0.10
    0.4%
    579
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.11
    0.02
    316
    +0.10
    0.03
    238
    +0.09
    0.03
    Negative Logits
    cult
    -0.76
    IDA
    -0.74
    Leaks
    -0.72
    DCS
    -0.71
    Hum
    -0.70
    developed
    -0.70
    lov
    -0.69
    Virgin
    -0.68
    Development
    -0.68
    Elect
    -0.67
    POSITIVE LOGITS
    ½
    0.70
     nil
    0.63
     sequential
    0.59
     undecided
    0.59
     consecutive
    0.57
    igsaw
    0.56
     randomized
    0.56
     aster
    0.56
     stray
    0.56
     elim
    0.56
    Activations Density 0.073%

    No Known Activations