© 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. 11994
    Prev
    Next
    INDEX
    Explanations

    descriptions of cooking or baking instructions

    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
    390
    +0.10
    0.5%
    207
    +0.10
    0.5%
    508
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    390
    +0.10
    0.03
    748
    +0.10
    0.02
    469
    +0.09
    0.02
    Negative Logits
    dar
    -0.84
    DERR
    -0.72
    enhagen
    -0.72
    someone
    -0.71
    iration
    -0.70
     awoken
    -0.69
    illard
    -0.68
    eton
    -0.64
     Technician
    -0.64
    ibe
    -0.64
    POSITIVE LOGITS
     chronological
    1.05
     manageable
    1.04
     halves
    0.91
     cohesive
    0.85
     subdiv
    0.83
     overlapping
    0.83
     concent
    0.82
     denominations
    0.81
     Pieces
    0.81
     categories
    0.81
    Activations Density 0.220%

    No Known Activations