© 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. 18300
    Prev
    Next
    INDEX
    Explanations

    sentences related to honoring or commemorating individuals or events

    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
    481
    +0.14
    0.6%
    275
    +0.11
    0.5%
    43
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.14
    0.04
    498
    +0.11
    0.04
    632
    +0.10
    0.03
    Negative Logits
    rets
    -0.66
    uments
    -0.65
    pretty
    -0.65
    SpaceEngineers
    -0.63
    miss
    -0.61
    competitive
    -0.61
    rage
    -0.60
    kind
    -0.60
    minster
    -0.60
    iour
    -0.59
    POSITIVE LOGITS
     we
    0.73
     researchers
    0.70
     however
    0.68
     Lets
    0.67
     Forbes
    0.67
     filmmakers
    0.67
     psychologists
    0.66
     please
    0.65
     physicists
    0.64
    iegel
    0.64
    Activations Density 0.217%

    No Known Activations