© 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. 41515
    Prev
    Next
    INDEX
    Explanations

    the name "Dean" in various contexts

    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
    167
    +0.11
    0.5%
    683
    +0.10
    0.4%
    152
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.11
    0.01
    696
    +0.10
    0.01
    682
    +0.09
    0.01
    Negative Logits
    TOR
    -0.86
    roxy
    -0.77
    nir
    -0.72
    enegger
    -0.71
    atoon
    -0.70
    olitan
    -0.66
    iculty
    -0.66
    aque
    -0.65
    */(
    -0.63
    ramid
    -0.63
    POSITIVE LOGITS
     Winchester
    1.08
     Ambrose
    0.80
    ette
    0.77
     Foster
    0.76
    bolt
    0.75
    ister
    0.72
    plan
    0.72
    ually
    0.72
     Beam
    0.71
     Ba
    0.70
    Activations Density 0.005%

    No Known Activations