© 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. 22882
    Prev
    Next
    INDEX
    Explanations

    references to small and large businesses

    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
    +0.14
    0.6%
    71
    +0.13
    0.6%
    459
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    722
    +0.14
    0.02
    71
    +0.13
    0.02
    762
    +0.10
    0.03
    Negative Logits
    imum
    -0.67
     Surgery
    -0.64
    imens
    -0.63
     Revision
    -0.61
     Ake
    -0.60
     Gau
    -0.59
     Tant
    -0.59
    anche
    -0.58
    apego
    -0.58
    ference
    -0.58
    POSITIVE LOGITS
     owners
    1.10
    folk
    1.01
     owner
    1.00
    owners
    0.97
     Owner
    0.86
    owner
    0.86
     enterprises
    0.86
    license
    0.84
    INESS
    0.83
     establishments
    0.82
    Activations Density 0.044%

    No Known Activations