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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 845
    Prev
    Next
    INDEX
    Explanations

    technical specifications of electronic devices

    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
    197
    +0.11
    0.5%
    202
    +0.11
    0.5%
    27
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.04
    197
    +0.11
    0.03
    289
    +0.11
    0.01
    Negative Logits
     funnel
    -0.75
     purse
    -0.74
     divers
    -0.70
    isson
    -0.69
     narr
    -0.69
    lihood
    -0.68
    SHIP
    -0.68
     needle
    -0.67
    steen
    -0.67
    ograms
    -0.67
    POSITIVE LOGITS
     firmware
    1.15
     macOS
    1.05
     Windows
    0.99
    Version
    0.98
    Windows
    0.98
     compatible
    0.98
     onwards
    0.97
     DirectX
    0.97
     Version
    0.95
     Linux
    0.94
    Activations Density 0.184%

    No Known Activations