© 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. 11059
    Prev
    Next
    INDEX
    Explanations

    legal terms and allegations

    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
    288
    +0.15
    0.7%
    96
    +0.11
    0.5%
    441
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.01
    631
    +0.11
    0.01
    441
    +0.10
    0.01
    Negative Logits
     Wilde
    -0.72
    ï¸
    -0.67
     Cage
    -0.66
    ³³³³³³³³³³³³³³³³
    -0.65
    knife
    -0.64
    OPLE
    -0.61
    manship
    -0.61
    UNCH
    -0.60
    ··
    -0.59
    pox
    -0.59
    POSITIVE LOGITS
    edly
    1.52
    heny
    1.36
    iance
    1.22
    orical
    1.07
    iances
    1.07
    rett
    1.02
    iant
    1.01
    orial
    1.00
    ations
    0.97
    rants
    0.90
    Activations Density 0.021%

    No Known Activations