© 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. 13577
    Prev
    Next
    INDEX
    Explanations

    actions or decisions related to conflict resolution

    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
    +0.40
    2.1%
    481
    +0.25
    1.3%
    266
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.40
    0.03
    266
    +0.25
    0.10
    351
    +0.13
    0.03
    Negative Logits
     HuffPost
    -0.71
     ÂŃ
    -0.67
     Manz
    -0.66
     BuzzFeed
    -0.63
     Johnston
    -0.62
     Rodham
    -0.60
     Goldstein
    -0.60
     Amtrak
    -0.60
     Greenwood
    -0.59
     Kaplan
    -0.59
    POSITIVE LOGITS
     alot
    1.12
     doesnt
    1.09
     dont
    1.05
     didnt
    0.90
     wont
    0.89
    nt
    0.86
     whats
    0.84
     thats
    0.78
     ;)
    0.78
     tho
    0.73
    Activations Density 1.182%

    No Known Activations