© 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 49152
    9. 8-RES_FS49152-JB
    11. 43065
    Prev
    Next
    INDEX
    Explanations

    HTML span tags used for styling elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    195
    +0.18
    0.8%
    526
    +0.12
    0.6%
    134
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.18
    0.01
    637
    +0.12
    0.01
    568
    +0.11
    0.01
    Negative Logits
    ysis
    -0.91
    phis
    -0.76
    illard
    -0.67
     reconc
    -0.65
    sie
    -0.65
    ĪĴ
    -0.65
    tical
    -0.64
    tics
    -0.63
    hran
    -0.62
     helicop
    -0.60
    POSITIVE LOGITS
    ning
    1.11
    ner
    1.00
    span
    0.94
    ners
    0.92
    ming
    0.88
    agy
    0.85
    ned
    0.80
    ider
    0.80
    med
    0.78
    rows
    0.77
    Activations Density 0.006%

    No Known Activations