© 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. 221
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    659
    +0.11
    0.5%
    95
    +0.10
    0.4%
    302
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.04
    335
    +0.10
    0.04
    81
    +0.09
    0.03
    Negative Logits
    wcs
    -0.87
    alysed
    -0.76
    translation
    -0.75
    ãĥĦ
    -0.73
    etheless
    -0.72
    artifacts
    -0.67
    drm
    -0.67
    âĹ¼
    -0.67
    inarily
    -0.66
    ihar
    -0.66
    POSITIVE LOGITS
     Smith
    1.02
     Powell
    1.00
     Baker
    0.98
     Johnson
    0.96
     Robinson
    0.95
     Roberts
    0.95
     Schw
    0.91
     Boone
    0.91
     Hughes
    0.91
     Olson
    0.90
    Activations Density 0.036%

    No Known Activations