© 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. 16893
    Prev
    Next
    INDEX
    Explanations

    social and political commentary on controversial issues

    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
    551
    +0.14
    0.6%
    529
    +0.10
    0.5%
    13
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.14
    0.06
    13
    +0.10
    0.04
    529
    +0.10
    0.03
    Negative Logits
     syndrome
    -0.76
     Syndrome
    -0.73
    vati
    -0.66
     pledging
    -0.64
     lucky
    -0.64
     Zah
    -0.62
    chu
    -0.61
     Rox
    -0.56
     unlucky
    -0.55
     improvised
    -0.55
    POSITIVE LOGITS
     disqual
    0.90
     ideally
    0.90
     be
    0.86
    ered
    0.83
    vet
    0.80
     logically
    0.80
     concern
    0.77
     suffice
    0.76
     theoretically
    0.76
    AFTA
    0.75
    Activations Density 0.085%

    No Known Activations