© 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. 13718
    Prev
    Next
    INDEX
    Explanations

    product names or technical terms related to mechanical components

    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
    373
    +0.16
    0.7%
    232
    +0.10
    0.4%
    750
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.16
    0.04
    373
    +0.10
    -0.01
    588
    +0.09
    0.03
    Negative Logits
     STATS
    -0.70
     recount
    -0.65
     quar
    -0.63
     directions
    -0.58
    Constructed
    -0.58
     Ou
    -0.58
     JFK
    -0.57
     inaction
    -0.56
     succession
    -0.56
     innocence
    -0.55
    POSITIVE LOGITS
    edo
    1.04
    oshenko
    0.97
    flix
    0.86
    hiba
    0.86
    asury
    0.84
    acco
    0.83
    nel
    0.82
    aron
    0.80
    agra
    0.77
    obl
    0.77
    Activations Density 0.080%

    No Known Activations