© 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. 13676
    Prev
    Next
    INDEX
    Explanations

    references to characters, locations, and titles from the Star Wars franchise

    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
    480
    +0.36
    2.4%
    711
    +0.09
    0.6%
    118
    +0.08
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.36
    0.12
    659
    +0.09
    0.09
    314
    +0.08
    -0.01
    Negative Logits
     Canaver
    -0.45
    staking
    -0.41
    arij
    -0.41
    pedia
    -0.39
    ratom
    -0.37
     FANTASY
    -0.37
     cautiously
    -0.37
     concise
    -0.37
    ERG
    -0.36
     archaeologists
    -0.36
    POSITIVE LOGITS
    )).
    0.68
    ").
    0.65
    ]).
    0.64
    )."
    0.64
    ]."
    0.63
    .).
    0.62
    %).
    0.61
    ).[
    0.60
    ).
    0.59
    ]);
    0.57
    Activations Density 1.279%

    No Known Activations