© 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 49152
    9. 8-RES_FS49152-JB
    11. 43093
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, particularly "Jacobs," indicating a focus on notable individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    316
    +0.14
    0.7%
    447
    +0.14
    0.6%
    46
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.14
    0.01
    46
    +0.14
    0.01
    659
    +0.13
    0.01
    Negative Logits
    onymous
    -0.87
    amental
    -0.79
    ŃĶ
    -0.79
    vironment
    -0.76
    arily
    -0.76
    acular
    -0.74
    anguage
    -0.74
    restrial
    -0.74
    ghai
    -0.73
    aceutical
    -0.72
    POSITIVE LOGITS
     Jacobs
    0.80
    son
    0.78
    mann
    0.73
    SON
    0.73
    ENS
    0.72
    aign
    0.69
    enegger
    0.69
    burg
    0.68
    tones
    0.67
    NET
    0.65
    Activations Density 0.002%

    No Known Activations