© 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. 21276
    Prev
    Next
    INDEX
    Explanations

    specific times mentioned in text

    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
    314
    +0.13
    0.6%
    373
    +0.13
    0.6%
    239
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.13
    0.05
    693
    +0.13
    0.04
    239
    +0.10
    0.04
    Negative Logits
    alog
    -0.60
    ctors
    -0.58
    imaru
    -0.56
     Lank
    -0.55
     pse
    -0.54
     delegation
    -0.54
    itionally
    -0.53
    olean
    -0.52
     ware
    -0.52
     meanwhile
    -0.52
    POSITIVE LOGITS
     apiece
    1.00
    noon
    0.91
    mph
    0.89
    point
    0.83
     behest
    0.83
    MHz
    0.78
     mph
    0.77
    nm
    0.76
    UTC
    0.76
    mast
    0.75
    Activations Density 0.072%

    No Known Activations