© 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. 2380
    Prev
    Next
    INDEX
    Explanations

    phrases related to coercion or intimidation

    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
    608
    +0.12
    0.5%
    83
    +0.10
    0.5%
    218
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.12
    0.03
    83
    +0.10
    0.02
    665
    +0.10
    0.02
    Negative Logits
    geist
    -0.73
     corpus
    -0.69
    imedia
    -0.66
    hetically
    -0.66
    der
    -0.64
    ILA
    -0.63
    thora
    -0.62
    zai
    -0.61
     capacitor
    -0.60
    alian
    -0.60
    POSITIVE LOGITS
     submission
    1.17
     believing
    0.91
     adulthood
    0.83
     ob
    0.83
    jection
    0.82
    livion
    0.79
     obedience
    0.76
    jected
    0.74
     extinction
    0.73
     accepting
    0.73
    Activations Density 0.049%

    No Known Activations