© 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 EvalsExportsinterp-engineNEWAPI 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. 14556
    Prev
    Next
    INDEX
    Explanations

    names with a specific pattern - "Ry" followed by a number

    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
    240
    +0.16
    0.7%
    29
    +0.10
    0.5%
    507
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.16
    0.01
    326
    +0.10
    0.01
    29
    +0.10
    0.01
    Negative Logits
     Hurricanes
    -0.75
     Edison
    -0.74
     Mandela
    -0.72
    IBLE
    -0.69
    imately
    -0.69
     [|
    -0.67
    mercial
    -0.67
     Fairfax
    -0.63
     Lois
    -0.62
    ITIES
    -0.61
    POSITIVE LOGITS
    obi
    0.97
    uko
    0.96
    oga
    0.96
    odan
    0.92
    Å«
    0.91
    gments
    0.90
    uu
    0.90
    stad
    0.89
    uki
    0.87
    ken
    0.86
    Activations Density 0.016%

    No Known Activations