© 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 12288
    9. 8-RES_FS12288-JB
    11. 594
    Prev
    Next
    INDEX
    Explanations

    information related to health, medical conditions, and scientific research

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    +0.18
    0.8%
    576
    +0.10
    0.5%
    69
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    576
    +0.18
    0.04
    142
    +0.10
    0.05
    236
    +0.10
    0.06
    Negative Logits
    phabet
    -0.95
    ittee
    -0.91
    ittees
    -0.90
    udeb
    -0.88
    gallery
    -0.84
    leased
    -0.84
    finished
    -0.83
    breaker
    -0.82
    Finish
    -0.82
    ISION
    -0.81
    POSITIVE LOGITS
     correlations
    1.19
     neural
    1.16
     correlation
    1.15
     epigen
    1.14
     genes
    1.07
     causation
    1.07
     genetic
    1.07
     genetics
    1.06
     physiological
    1.03
     biologically
    1.03
    Activations Density 0.689%

    No Known Activations