© 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 49152
    9. 8-RES_FS49152-JB
    11. 26638
    Prev
    Next
    INDEX
    Explanations

    instances of the word "there" and its variations in context

    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
    481
    +0.14
    0.6%
    377
    +0.11
    0.5%
    182
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.14
    0.01
    377
    +0.11
    0.01
    651
    +0.09
    0.01
    Negative Logits
    agara
    -0.83
    orously
    -0.80
    mens
    -0.78
    ual
    -0.78
    icer
    -0.74
    phal
    -0.73
    ahime
    -0.72
    ivities
    -0.71
    egu
    -0.70
    bern
    -0.70
    POSITIVE LOGITS
    abouts
    1.00
     beside
    0.87
    tical
    0.71
     atop
    0.68
     Mellon
    0.68
     amongst
    0.66
     somewhere
    0.66
    tics
    0.66
     roadside
    0.63
     corner
    0.63
    Activations Density 0.014%

    No Known Activations