© 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. 18121
    Prev
    Next
    INDEX
    Explanations

    advice or instructions related to technological tasks

    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
    447
    +0.13
    0.6%
    46
    +0.11
    0.5%
    736
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.13
    0.05
    588
    +0.11
    0.05
    151
    +0.10
    0.05
    Negative Logits
    aunder
    -0.72
    hal
    -0.69
    nuclear
    -0.69
    uton
    -0.68
    iverpool
    -0.67
    uclear
    -0.66
    tein
    -0.66
    arnaev
    -0.64
    士
    -0.64
    Action
    -0.64
    POSITIVE LOGITS
     owing
    0.81
     due
    0.80
     bec
    0.78
     because
    0.77
     intermitt
    0.75
     sounding
    0.74
     lately
    0.73
     bog
    0.72
     academ
    0.71
     sometimes
    0.71
    Activations Density 0.253%

    No Known Activations