© 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. 9072
    Prev
    Next
    INDEX
    Explanations

    references to the company Amazon

    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
    343
    +0.16
    0.7%
    288
    +0.12
    0.6%
    585
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.16
    0.03
    585
    +0.12
    0.02
    520
    +0.11
    0.02
    Negative Logits
    boarding
    -0.74
     orally
    -0.72
    etting
    -0.71
     sober
    -0.69
     Schne
    -0.68
    bil
    -0.68
     Rasm
    -0.66
    ROR
    -0.65
    cised
    -0.65
     Bour
    -0.63
    POSITIVE LOGITS
     Studios
    0.88
     Prime
    0.84
    Prime
    0.79
    Fresh
    0.79
     Kindle
    0.79
     Echo
    0.78
     Mechanical
    0.78
    conn
    0.76
    Bas
    0.76
     warehouses
    0.73
    Activations Density 0.016%

    No Known Activations