Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 7640
    Prev
    Next
    INDEX
    Explanations

    URLs leading to images

    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
    107
    +0.14
    0.6%
    640
    +0.14
    0.6%
    749
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.14
    0.04
    160
    +0.14
    0.03
    648
    +0.12
    0.02
    Negative Logits
     Turing
    -0.75
     Initiative
    -0.71
     Scientist
    -0.70
     Paraly
    -0.69
     Survivors
    -0.69
     Objective
    -0.68
     Pigs
    -0.68
     Sanctuary
    -0.67
     TAMADRA
    -0.67
     Zeal
    -0.66
    POSITIVE LOGITS
    images
    1.24
    uploads
    1.21
    icons
    1.11
    download
    1.08
    img
    1.07
    products
    1.06
    papers
    1.05
    Accessory
    1.02
    tnc
    1.02
    assets
    1.01
    Activations Density 0.024%

    No Known Activations