© 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 EvalsExportsAPI 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. 56
    Prev
    Next
    INDEX
    Explanations

    verbs in the passive voice

    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
    102
    +0.15
    0.7%
    55
    +0.13
    0.6%
    393
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.15
    0.06
    55
    +0.13
    0.05
    208
    +0.13
    0.04
    Negative Logits
    rones
    -0.78
    anwhile
    -0.77
    culosis
    -0.71
    rella
    -0.65
    ãĥ¼ãĥ«
    -0.64
    iasco
    -0.63
     promise
    -0.62
    rouse
    -0.62
     rall
    -0.61
    osate
    -0.61
    POSITIVE LOGITS
     able
    0.98
    leeve
    0.82
     influenced
    0.75
     helpful
    0.75
     regarded
    0.74
     quite
    0.73
     considered
    0.72
     extremely
    0.71
    fit
    0.69
     invaluable
    0.69
    Activations Density 0.097%

    No Known Activations