© 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. 16930
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and community discussions

    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
    +0.39
    1.9%
    102
    +0.14
    0.7%
    7
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.39
    0.08
    55
    +0.14
    0.07
    718
    +0.12
    0.06
    Negative Logits
     Flavoring
    -0.90
    ngth
    -0.86
    essor
    -0.83
     Awakens
    -0.74
    ividual
    -0.73
    anwhile
    -0.72
    each
    -0.66
    velt
    -0.65
     openings
    -0.65
    idences
    -0.64
    POSITIVE LOGITS
     evident
    1.04
     understandable
    0.90
     applicable
    0.88
     obvious
    0.87
     prevalent
    0.86
     feasible
    0.85
     irrelevant
    0.84
     worrisome
    0.83
     fraught
    0.82
     apparent
    0.82
    Activations Density 0.240%

    No Known Activations