© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 20083
    Prev
    Next
    INDEX
    Explanations

    food-related terms and names of food items

    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
    36
    +0.17
    0.8%
    372
    +0.12
    0.6%
    343
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.17
    0.04
    659
    +0.12
    0.04
    57
    +0.11
    0.03
    Negative Logits
    lings
    -0.67
     optics
    -0.66
    lication
    -0.66
    geist
    -0.66
     Emin
    -0.65
    nian
    -0.65
    liners
    -0.64
     Mysteries
    -0.64
     Investigator
    -0.62
    ragon
    -0.62
    POSITIVE LOGITS
    vern
    1.20
    ñ
    1.14
    VE
    1.10
    ctions
    1.09
    plin
    1.09
    iley
    1.08
    vel
    1.04
    ves
    1.04
    uble
    1.03
    pling
    1.02
    Activations Density 0.076%

    No Known Activations