© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1396
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptive terms related to behavioral traits or characteristics

    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
    46
    +0.10
    0.5%
    420
    +0.10
    0.5%
    756
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.10
    0.05
    288
    +0.10
    0.04
    588
    +0.10
    0.03
    Negative Logits
    tains
    -0.71
    ocular
    -0.66
    empt
    -0.64
    Clar
    -0.63
    ozo
    -0.63
    hon
    -0.62
    othe
    -0.61
    zyme
    -0.61
    odder
    -0.61
    ioxide
    -0.61
    POSITIVE LOGITS
    luster
    0.89
    nesses
    0.82
     owing
    0.75
    mson
    0.75
     miser
    0.72
     due
    0.72
     blacks
    0.66
     Worse
    0.65
     blight
    0.65
     Pradesh
    0.65
    Activations Density 0.165%

    No Known Activations