© 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. 12390
    Prev
    Next
    INDEX
    Explanations

    memorable life experiences or significant historical events

    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
    480
    +0.43
    2.1%
    714
    +0.10
    0.5%
    669
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.43
    -0.00
    266
    +0.10
    0.10
    351
    +0.09
    0.04
    Negative Logits
    etheless
    -0.90
    SPONSORED
    -0.69
    ]).
    -0.65
     respectively
    -0.65
    ''.
    -0.64
    `.
    -0.63
    .''.
    -0.63
    )))
    -0.61
     GOODMAN
    -0.61
    zik
    -0.60
    POSITIVE LOGITS
     loved
    0.61
     countless
    0.60
     nurt
    0.58
     buzzing
    0.58
     endlessly
    0.57
     pian
    0.57
     factories
    0.56
     swe
    0.56
     everywhere
    0.56
     cub
    0.56
    Activations Density 1.603%

    No Known Activations