© 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. 7832
    Prev
    Next
    INDEX
    Explanations

    dates and events like games, attacks, or sentences

    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
    +0.13
    0.6%
    245
    +0.11
    0.5%
    458
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    141
    +0.13
    0.03
    430
    +0.11
    0.04
    472
    +0.10
    0.02
    Negative Logits
    laim
    -0.79
    anan
    -0.70
    cientious
    -0.69
    etimes
    -0.69
    */(
    -0.68
    intend
    -0.66
    kef
    -0.65
    cules
    -0.63
    geries
    -0.63
    certain
    -0.63
    POSITIVE LOGITS
    east
    0.76
     onwards
    0.65
     onward
    0.63
    04
    0.63
     coasts
    0.61
     drills
    0.59
     lows
    0.59
     arrives
    0.59
    004
    0.59
    Tokens
    0.58
    Activations Density 0.121%

    No Known Activations