© 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. 17574
    Prev
    Next
    INDEX
    Explanations

    the word "to" and numbers related to statistics

    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
    241
    +0.11
    0.5%
    27
    +0.10
    0.4%
    159
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    305
    +0.11
    0.03
    433
    +0.10
    0.03
    297
    +0.09
    0.02
    Negative Logits
    ocus
    -0.65
     reconc
    -0.65
    ciation
    -0.65
    atos
    -0.60
     quotations
    -0.60
     interchange
    -0.60
    Sov
    -0.60
    ////////
    -0.58
    Translation
    -0.57
     CLIENT
    -0.56
    POSITIVE LOGITS
     age
    0.76
    ileged
    0.75
     youngest
    0.71
     younger
    0.69
    young
    0.68
     teens
    0.67
     2050
    0.66
     aged
    0.66
     2030
    0.65
    eligible
    0.64
    Activations Density 0.068%

    No Known Activations