© 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. 26637
    Prev
    Next
    INDEX
    Explanations

    phrases pertaining to quantity and measurement

    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
    463
    +0.15
    0.7%
    674
    +0.10
    0.5%
    57
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    463
    +0.15
    0.04
    449
    +0.10
    0.02
    408
    +0.10
    0.03
    Negative Logits
    iHUD
    -0.79
    hig
    -0.71
    Interstitial
    -0.66
    $.
    -0.66
    inery
    -0.65
    ilan
    -0.65
    essage
    -0.65
    hover
    -0.63
    porter
    -0.63
    senal
    -0.62
    POSITIVE LOGITS
    ?
    1.67
    ?"
    1.52
    ?:
    1.51
    ?!
    1.50
    ?)
    1.49
    ?'
    1.46
    !?
    1.43
    ?),
    1.42
    ?]
    1.41
    ?!"
    1.39
    Activations Density 0.075%

    No Known Activations