© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9018
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or locations in relation to each other

    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
    157
    +0.13
    0.6%
    314
    +0.12
    0.5%
    526
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.13
    0.03
    758
    +0.12
    0.02
    696
    +0.11
    0.02
    Negative Logits
    iments
    -0.72
    ionage
    -0.70
    ufact
    -0.69
    ettel
    -0.68
    natureconservancy
    -0.67
     destro
    -0.66
    acca
    -0.65
     mathemat
    -0.62
    omething
    -0.61
    odka
    -0.61
    POSITIVE LOGITS
    about
    1.31
    abouts
    1.25
    trip
    1.22
    table
    1.21
    ups
    1.03
     rob
    0.99
    worms
    0.98
    up
    0.91
    worm
    0.86
    Robin
    0.86
    Activations Density 0.024%

    No Known Activations