© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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 3072
    9. 8-RES_FS3072-JB
    11. 257
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions or considerations around sensitive or controversial topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    92
    +0.12
    0.5%
    331
    +0.10
    0.5%
    550
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.12
    0.08
    665
    +0.10
    0.09
    92
    +0.10
    0.06
    Negative Logits
    ij士
    -0.73
    court
    -0.69
    teness
    -0.68
    txt
    -0.63
     Kissinger
    -0.63
     Boat
    -0.62
    none
    -0.62
    OTOS
    -0.61
     Hicks
    -0.61
    clave
    -0.60
    POSITIVE LOGITS
     interact
    0.96
     interpret
    0.95
     behave
    0.94
     handle
    0.92
     cope
    0.92
     communicate
    0.90
     interpreting
    0.90
     coping
    0.89
     navigate
    0.88
     relate
    0.85
    Activations Density 1.226%

    No Known Activations