© 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. 10631
    Prev
    Next
    INDEX
    Explanations

    words related to academic performance and assessment

    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
    762
    +0.12
    0.5%
    709
    +0.10
    0.5%
    156
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.12
    0.04
    221
    +0.10
    0.03
    646
    +0.10
    0.02
    Negative Logits
     guiName
    -0.71
    ivalry
    -0.60
     Ferry
    -0.56
    utenberg
    -0.56
    Introduced
    -0.54
     Settlement
    -0.54
    iken
    -0.53
    Point
    -0.53
     Fifth
    -0.53
     Colomb
    -0.52
    POSITIVE LOGITS
    )
    1.56
    )-
    1.47
    -)
    1.46
    !)
    1.45
    *)
    1.43
    )!
    1.41
    ?)
    1.39
    )'
    1.37
    )?
    1.35
    )—
    1.26
    Activations Density 0.226%

    No Known Activations