© 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. 22385
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and exchanges

    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
    481
    +0.17
    0.8%
    487
    +0.11
    0.5%
    93
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.17
    0.04
    659
    +0.11
    0.05
    93
    +0.10
    0.04
    Negative Logits
    idays
    -0.71
    ovych
    -0.65
    ibling
    -0.64
     tremend
    -0.61
    ¯
    -0.61
     toget
    -0.58
     shine
    -0.58
    ¥µ
    -0.57
     insecurity
    -0.57
     Shine
    -0.57
    POSITIVE LOGITS
    ulhu
    1.23
    ioxide
    0.93
    ortium
    0.90
    ornia
    0.84
     Unch
    0.81
    xus
    0.80
    arette
    0.79
    aign
    0.75
    berus
    0.71
    ervatives
    0.70
    Activations Density 0.373%

    No Known Activations