© 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. 8829
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or places

    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
    314
    +0.13
    0.6%
    162
    +0.11
    0.5%
    523
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.13
    0.02
    354
    +0.11
    0.02
    708
    +0.10
    0.02
    Negative Logits
    encies
    -0.78
     conflic
    -0.71
     Seym
    -0.71
    nces
    -0.70
    cffff
    -0.69
    milo
    -0.67
     alloy
    -0.67
    illian
    -0.67
     circumstance
    -0.67
    anyahu
    -0.66
    POSITIVE LOGITS
    through
    1.21
    about
    1.13
    ways
    1.04
    away
    1.02
    abouts
    0.98
    er
    0.94
    ers
    0.94
    bow
    0.91
    way
    0.89
    own
    0.88
    Activations Density 0.021%

    No Known Activations