© 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. 19652
    Prev
    Next
    INDEX
    Explanations

    mathematics-related terms

    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
    481
    +0.14
    0.6%
    447
    +0.12
    0.5%
    680
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.06
    644
    +0.12
    0.05
    455
    +0.10
    0.05
    Negative Logits
    entimes
    -0.89
    inia
    -0.71
    riched
    -0.70
    alone
    -0.63
    ornings
    -0.62
    ocally
    -0.61
    evil
    -0.61
    attery
    -0.60
    venge
    -0.60
    odied
    -0.60
    POSITIVE LOGITS
    iest
    0.98
    liest
    0.96
     portion
    0.90
     section
    0.87
     curve
    0.83
     behind
    0.82
     outline
    0.82
     below
    0.81
     specs
    0.81
     timeline
    0.81
    Activations Density 0.327%

    No Known Activations