© 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. 18359
    Prev
    Next
    INDEX
    Explanations

    descriptions of characters and actions in a kindergarten setting

    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
    373
    +0.18
    0.9%
    494
    +0.10
    0.5%
    613
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.18
    0.02
    391
    +0.10
    0.01
    100
    +0.09
    0.01
    Negative Logits
    Advertisements
    -0.85
    undy
    -0.79
    âĹ¼
    -0.76
    ascript
    -0.74
    HL
    -0.68
    Insert
    -0.68
    External
    -0.66
    rans
    -0.64
    etts
    -0.64
    ariat
    -0.64
    POSITIVE LOGITS
     Seeking
    0.66
     fugitive
    0.64
     learns
    0.64
     confronts
    0.62
    adiator
    0.61
     Makoto
    0.60
     FIGHT
    0.56
    Adds
    0.55
     hacker
    0.55
     battled
    0.55
    Activations Density 0.082%

    No Known Activations