© 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. 21157
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "The story of" and detailing historical or fictional narratives

    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
    393
    +0.13
    0.6%
    561
    +0.12
    0.5%
    669
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.03
    669
    +0.12
    0.03
    561
    +0.10
    0.03
    Negative Logits
    reau
    -0.89
    hement
    -0.86
    oreal
    -0.78
    rouse
    -0.74
    SpaceEngineers
    -0.73
    ascus
    -0.72
    ©¶æ¥µ
    -0.70
    ngth
    -0.68
    pour
    -0.68
     pose
    -0.68
    POSITIVE LOGITS
     heroism
    1.09
     how
    0.91
     mankind
    0.77
     overcoming
    0.74
     untold
    0.73
     why
    0.72
     unsolved
    0.72
     humankind
    0.70
     Artemis
    0.69
     Lazarus
    0.69
    Activations Density 0.110%

    No Known Activations