© 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. 1825
    Prev
    Next
    INDEX
    Explanations

    technical and detailed information related to defense, finance, and medical studies

    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
    +0.36
    1.9%
    314
    +0.09
    0.5%
    365
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.36
    -0.02
    547
    +0.09
    0.04
    680
    +0.08
    0.04
    Negative Logits
    MSN
    -0.54
     brakes
    -0.51
     fitt
    -0.50
     robbers
    -0.49
     veget
    -0.48
     awa
    -0.48
     wheelchair
    -0.47
     matured
    -0.47
     bodily
    -0.46
     headlights
    -0.46
    POSITIVE LOGITS
    .).
    0.91
    )).
    0.82
    ]).
    0.78
    ).
    0.75
    }.
    0.74
    >.
    0.69
    ].
    0.68
    ).[
    0.66
    $.
    0.60
     ).
    0.60
    Activations Density 1.543%

    No Known Activations