© 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. 22615
    Prev
    Next
    INDEX
    Explanations

    terms related to fuel prices, inflation, and economic indicators

    oai_token-act-pair · gpt-4o-miniTriggered 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
    +0.13
    0.6%
    595
    +0.09
    0.4%
    209
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.09
    147
    +0.09
    0.04
    594
    +0.09
    0.04
    Negative Logits
    irlf
    -0.78
    cific
    -0.72
     pedoph
    -0.66
    ulhu
    -0.64
    ochet
    -0.64
     Canaver
    -0.64
     pseud
    -0.63
     Milo
    -0.63
    enge
    -0.62
     Lovecraft
    -0.62
    POSITIVE LOGITS
     accounted
    1.03
     sector
    1.02
     revenues
    0.92
    sector
    0.91
     stocks
    0.91
     sectors
    0.87
     shipments
    0.87
     earnings
    0.86
     industries
    0.86
     sales
    0.85
    Activations Density 0.488%

    No Known Activations