© 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. 9003
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to a group of people

    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
    +0.17
    0.8%
    762
    +0.10
    0.5%
    671
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.17
    0.07
    718
    +0.10
    0.08
    354
    +0.10
    0.07
    Negative Logits
     profitability
    -0.73
     Affordable
    -0.65
     Fortress
    -0.64
     Ribbon
    -0.64
     Estate
    -0.63
    Cu
    -0.63
     Cance
    -0.62
     AMERICA
    -0.62
     mascot
    -0.61
     Mansion
    -0.59
    POSITIVE LOGITS
     perceive
    1.16
     intu
    1.16
     understand
    1.15
     subconscious
    1.14
     infer
    1.10
     understanding
    1.09
     instinctively
    1.09
     know
    1.08
     wonder
    1.07
     wondering
    1.07
    Activations Density 0.505%

    No Known Activations