© 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. 13048
    Prev
    Next
    INDEX
    Explanations

    claims or statements being disputed or contradicted

    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
    +0.14
    0.6%
    81
    +0.10
    0.4%
    191
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.14
    0.03
    43
    +0.10
    0.03
    546
    +0.10
    0.03
    Negative Logits
    é¾
    -0.63
    answered
    -0.62
    cko
    -0.60
    \/
    -0.60
    arial
    -0.59
     Became
    -0.59
    -------
    -0.57
    Accept
    -0.57
    minster
    -0.56
     Closed
    -0.56
    POSITIVE LOGITS
     but
    1.23
    but
    1.16
     nor
    0.92
     BUT
    0.85
    But
    0.80
    although
    0.79
     though
    0.78
     But
    0.76
    though
    0.73
     secondly
    0.72
    Activations Density 0.127%

    No Known Activations