© 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. 16858
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislation or regulations

    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
    745
    +0.11
    0.5%
    61
    +0.09
    0.4%
    546
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.11
    0.06
    762
    +0.09
    0.06
    526
    +0.09
    -0.00
    Negative Logits
     Methodist
    -0.74
     Guinness
    -0.69
    rontal
    -0.64
     predecessor
    -0.63
     memos
    -0.61
     presided
    -0.61
     chronological
    -0.60
     Anthrop
    -0.59
     shorthand
    -0.58
     Tome
    -0.58
    POSITIVE LOGITS
     foothold
    0.96
     exploit
    0.87
     theirs
    0.81
    usive
    0.80
     threaten
    0.79
     infringing
    0.79
     thrive
    0.78
     exploiting
    0.77
    volent
    0.76
     unchecked
    0.73
    Activations Density 0.467%

    No Known Activations