© 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. 1979
    Prev
    Next
    INDEX
    Explanations

    descriptions of video games and gaming features

    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
    451
    +0.14
    0.6%
    674
    +0.11
    0.5%
    447
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.14
    0.05
    679
    +0.11
    0.10
    756
    +0.11
    -0.04
    Negative Logits
     Slate
    -0.94
     Ramsay
    -0.91
     BuzzFeed
    -0.84
    )—
    -0.81
     Watkins
    -0.81
     Baker
    -0.80
     ÂŃ
    -0.80
    —
    -0.80
    —"
    -0.79
     Burke
    -0.78
    POSITIVE LOGITS
    ´
    1.10
     resear
    1.02
     dont
    0.99
     happ
    0.98
     analyse
    0.96
    iour
    0.95
    pecially
    0.94
     secondly
    0.94
     till
    0.93
     android
    0.92
    Activations Density 2.405%

    No Known Activations