© 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. 4103
    Prev
    Next
    INDEX
    Explanations

    information related to news articles and incidents happening in different countries

    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
    +0.25
    1.3%
    447
    +0.19
    1.0%
    87
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.25
    0.07
    281
    +0.19
    0.04
    680
    +0.11
    0.03
    Negative Logits
    )))
    -0.63
    )?
    -0.61
     tomorrow
    -0.61
    FIX
    -0.57
     sooner
    -0.56
     depends
    -0.55
    ////////////////////////////////
    -0.54
    onday
    -0.54
    ?ãĢį
    -0.54
     tonight
    -0.53
    POSITIVE LOGITS
    schild
    0.59
    FTWARE
    0.58
    ixty
    0.57
     controvers
    0.55
    itled
    0.53
     unsuccessfully
    0.53
     Guess
    0.52
     announcing
    0.50
     Overt
    0.49
    igate
    0.49
    Activations Density 1.135%

    No Known Activations