© 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. 7817
    Prev
    Next
    INDEX
    Explanations

    words related to breaking down, analyzing, or deconstructing complex concepts or structures, such as systems, mechanisms, texts, and individuals

    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
    439
    +0.10
    0.4%
    512
    +0.10
    0.4%
    323
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    337
    +0.10
    0.01
    263
    +0.10
    0.01
    192
    +0.09
    0.01
    Negative Logits
    arak
    -0.68
    mong
    -0.62
    nder
    -0.62
    nor
    -0.60
    jab
    -0.59
     recall
    -0.59
     Patron
    -0.58
    ught
    -0.58
     Promise
    -0.58
    visor
    -0.58
    POSITIVE LOGITS
     barriers
    0.86
    sheets
    0.83
    taining
    0.75
    stairs
    0.73
    shit
    0.71
    baugh
    0.69
    inately
    0.68
    casts
    0.67
    grades
    0.67
     stairs
    0.67
    Activations Density 0.026%

    No Known Activations