© 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. 5661
    Prev
    Next
    INDEX
    Explanations

    legal terms and regulations

    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
    640
    +0.20
    0.9%
    160
    +0.19
    0.9%
    314
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.20
    0.04
    442
    +0.19
    0.03
    640
    +0.16
    0.03
    Negative Logits
     Haku
    -0.74
     Tent
    -0.69
    ĸļ
    -0.69
     bowed
    -0.69
     Solomon
    -0.68
     Story
    -0.67
     Slug
    -0.67
     Liter
    -0.66
     Shinzo
    -0.66
     fmt
    -0.65
    POSITIVE LOGITS
    enough
    1.28
    administ
    1.23
    appropriate
    1.21
    individual
    1.18
    different
    1.15
    together
    1.13
    need
    1.13
    acqu
    1.11
    recomm
    1.11
    subject
    1.09
    Activations Density 0.039%

    No Known Activations