© 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 EvalsExportsinterp-engineNEWAPI 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. 22871
    Prev
    Next
    INDEX
    Explanations

    references to leadership and influential roles within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    431
    +0.10
    0.5%
    481
    +0.10
    0.5%
    510
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    431
    +0.10
    0.04
    510
    +0.10
    0.05
    575
    +0.10
    0.06
    Negative Logits
    etheless
    -0.68
    repre
    -0.62
     ãĢĮ
    -0.59
    ength
    -0.58
    arnaev
    -0.57
     :=
    -0.57
    bably
    -0.56
    upon
    -0.56
    utenberg
    -0.56
    umbai
    -0.55
    POSITIVE LOGITS
    ",
    1.72
    "—
    1.68
    "
    1.68
    "?
    1.68
    ")
    1.61
    "!
    1.60
    ").
    1.57
    ":
    1.57
    "-
    1.56
    ".
    1.55
    Activations Density 0.390%

    No Known Activations