© 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 EvalsExportsinterp-engineNEWAPI 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. 4993
    Prev
    Next
    INDEX
    Explanations

    characters and sequences in a specific non-English text

    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
    +0.42
    2.2%
    87
    +0.23
    1.2%
    447
    +0.22
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    103
    +0.42
    0.04
    266
    +0.23
    0.03
    284
    +0.22
    0.03
    Negative Logits
     disadvant
    -0.77
     occas
    -0.72
     athlet
    -0.70
     contrace
    -0.69
     agre
    -0.69
     conclud
    -0.68
     challeng
    -0.68
     undermin
    -0.67
     hemor
    -0.66
     skelet
    -0.66
    POSITIVE LOGITS
    к
    1.10
    в
    1.02
    Ì
    1.01
    м
    1.00
    н
    0.98
    л
    0.96
     âĢº
    0.94
    Ñĥ
    0.94
    и
    0.93
    ÑĤ
    0.93
    Activations Density 0.104%

    No Known Activations