© 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. 13914
    Prev
    Next
    INDEX
    Explanations

    a pattern of numbers with ascending values

    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
    373
    +0.30
    1.6%
    459
    +0.10
    0.5%
    378
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.30
    -0.01
    176
    +0.10
    0.02
    513
    +0.09
    0.02
    Negative Logits
     convict
    -0.57
     ec
    -0.54
     conv
    -0.51
     wholes
    -0.51
    zos
    -0.51
    cot
    -0.49
     advis
    -0.48
    compan
    -0.48
     esc
    -0.47
    phen
    -0.47
    POSITIVE LOGITS
    âĶĢâĶĢâĶĢâĶĢ
    0.66
    inki
    0.65
     Conclusion
    0.65
    Conclusion
    0.63
    jamin
    0.61
     =================
    0.61
     Explicit
    0.59
    Marginal
    0.59
    Ability
    0.59
    ________________________
    0.58
    Activations Density 0.046%

    No Known Activations