© 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. 18671
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of persons

    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%
    548
    +0.12
    0.6%
    159
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.06
    353
    +0.12
    0.05
    65
    +0.12
    0.05
    Negative Logits
    Magikarp
    -0.73
    SpaceEngineers
    -0.73
    udeb
    -0.72
    catentry
    -0.72
    20439
    -0.70
    Reviewer
    -0.69
    href
    -0.69
     [&
    -0.67
     newsp
    -0.67
    ebted
    -0.66
    POSITIVE LOGITS
    hower
    0.80
    mania
    0.70
    endish
    0.67
    sonian
    0.66
    erson
    0.66
     Sachs
    0.65
     sighed
    0.65
    ashtra
    0.63
     Dynamics
    0.63
     loves
    0.61
    Activations Density 0.243%

    No Known Activations