© 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. 15681
    Prev
    Next
    INDEX
    Explanations

    verbs related to handling difficult situations or challenges

    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
    355
    +0.09
    0.4%
    763
    +0.09
    0.4%
    257
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.09
    0.02
    761
    +0.09
    0.01
    125
    +0.09
    0.01
    Negative Logits
    prints
    -0.74
    tein
    -0.67
     livest
    -0.65
    prem
    -0.63
    lav
    -0.63
    friend
    -0.61
     Lomb
    -0.61
    nic
    -0.60
     Benef
    -0.59
    ĻĤ
    -0.58
    POSITIVE LOGITS
     adequately
    0.99
    ively
    0.79
    heet
    0.79
     cope
    0.78
    atively
    0.75
    itute
    0.74
    ptin
    0.74
     pressures
    0.74
    itely
    0.73
     withd
    0.72
    Activations Density 0.042%

    No Known Activations