© 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. 1330
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Shane"

    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
    636
    +0.14
    0.6%
    274
    +0.10
    0.5%
    382
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    636
    +0.14
    0.02
    659
    +0.10
    0.02
    419
    +0.10
    0.01
    Negative Logits
    yrinth
    -0.92
    insula
    -0.84
    ktop
    -0.80
    rontal
    -0.80
    ollower
    -0.78
    é¾įå¥ij士
    -0.77
    ¥µ
    -0.76
    女
    -0.74
    iatrics
    -0.74
    Īè
    -0.71
    POSITIVE LOGITS
     McMahon
    0.98
     Shane
    0.84
     Dixon
    0.77
     Bauer
    0.76
     Braun
    0.75
     Greene
    0.75
     Leone
    0.74
     Daniels
    0.73
     Simmons
    0.71
     Meadows
    0.71
    Activations Density 0.016%

    No Known Activations