© 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. 11074
    Prev
    Next
    INDEX
    Explanations

    words related to scientific experiments or processes

    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
    447
    +0.15
    0.7%
    69
    +0.09
    0.4%
    534
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    604
    +0.15
    0.03
    43
    +0.09
    0.03
    529
    +0.09
    0.04
    Negative Logits
    alone
    -0.67
    sis
    -0.67
    Cola
    -0.63
    border
    -0.61
    cour
    -0.61
    oland
    -0.60
    roller
    -0.59
    arat
    -0.59
    align
    -0.59
    shield
    -0.58
    POSITIVE LOGITS
     glances
    0.87
     valuable
    0.82
     funds
    0.81
     scraps
    0.78
     copies
    0.76
     priceless
    0.75
     stolen
    0.73
     snippets
    0.73
     assets
    0.73
     information
    0.72
    Activations Density 0.186%

    No Known Activations