© 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. 1484
    Prev
    Next
    INDEX
    Explanations

    mentions of doors, borders, or deals being closed

    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
    636
    +0.13
    0.6%
    665
    +0.11
    0.5%
    246
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    636
    +0.13
    0.03
    3
    +0.11
    0.02
    159
    +0.09
    0.02
    Negative Logits
     Samoa
    -0.74
    ãĥīãĥ©ãĤ´ãĥ³
    -0.71
     guiIcon
    -0.67
    ogram
    -0.64
     Laurie
    -0.61
     Uriel
    -0.60
     Gry
    -0.60
    REP
    -0.60
    nai
    -0.59
     fodder
    -0.56
    POSITIVE LOGITS
     doors
    1.16
     loopholes
    0.98
     arteries
    0.96
     door
    0.96
     valves
    0.92
     curtains
    0.89
     gap
    0.87
     gaps
    0.86
     throttle
    0.85
    door
    0.84
    Activations Density 0.050%

    No Known Activations