© 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. 17596
    Prev
    Next
    INDEX
    Explanations

    mentions of attributes or characteristics of a subject (for instance, music styles or historical periods)

    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
    +0.15
    0.7%
    688
    +0.10
    0.4%
    393
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    345
    +0.15
    0.03
    362
    +0.10
    0.03
    688
    +0.10
    0.03
    Negative Logits
    Enable
    -0.79
    ****
    -0.76
    ILE
    -0.74
    Yan
    -0.74
    IFIED
    -0.74
    VER
    -0.73
    Brow
    -0.73
    WHO
    -0.73
    imal
    -0.72
    Lock
    -0.72
    POSITIVE LOGITS
     attendant
    1.41
     allies
    1.25
     associated
    1.20
     accompanying
    1.18
     successors
    1.16
     derivatives
    1.14
     il
    1.13
     affiliates
    1.11
     surroundings
    1.10
     equivalents
    1.08
    Activations Density 0.075%

    No Known Activations