© 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. 22807
    Prev
    Next
    INDEX
    Explanations

    specific times and dates related to events or broadcasts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    373
    +0.25
    1.2%
    140
    +0.09
    0.4%
    378
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.25
    -0.01
    176
    +0.09
    0.02
    523
    +0.09
    0.03
    Negative Logits
    cow
    -0.63
    etimes
    -0.62
    netflix
    -0.61
    luaj
    -0.60
    minecraft
    -0.60
    yrights
    -0.59
    ancial
    -0.57
    avorite
    -0.56
    cientious
    -0.56
    Blade
    -0.55
    POSITIVE LOGITS
     onward
    0.77
     onwards
    0.76
    *:
    0.68
     Ibid
    0.68
     Puzzles
    0.67
     CONTIN
    0.67
     partName
    0.66
    %:
    0.64
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.64
    .—
    0.62
    Activations Density 0.077%

    No Known Activations