© 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. 8572
    Prev
    Next
    INDEX
    Explanations

    the word "whom" in the 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
    430
    +0.13
    0.6%
    207
    +0.12
    0.5%
    589
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    757
    +0.13
    0.01
    30
    +0.12
    0.01
    59
    +0.11
    0.01
    Negative Logits
    pad
    -0.77
    forcing
    -0.73
    DEN
    -0.72
    rid
    -0.68
    jad
    -0.67
    fix
    -0.66
    case
    -0.65
    lag
    -0.64
    tight
    -0.64
    termin
    -0.64
    POSITIVE LOGITS
    soever
    1.95
    selves
    0.86
     dearly
    0.79
     whom
    0.75
    onga
    0.70
     alike
    0.66
     coh
    0.63
     shares
    0.63
    usalem
    0.62
     vou
    0.62
    Activations Density 0.007%

    No Known Activations