© 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 EvalsExportsAPI 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. 19754
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software or system settings

    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
    101
    +0.13
    0.6%
    342
    +0.12
    0.5%
    461
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.13
    0.03
    396
    +0.12
    0.03
    5
    +0.09
    0.03
    Negative Logits
    kees
    -0.97
    flies
    -0.87
    zz
    -0.82
     Shroud
    -0.78
     Kush
    -0.76
     Gamble
    -0.73
    Kn
    -0.73
    Hack
    -0.72
    Cu
    -0.71
     cloves
    -0.71
    POSITIVE LOGITS
     peripheral
    0.90
     conventional
    0.90
    ventional
    0.85
     genuine
    0.84
     Regional
    0.84
    english
    0.83
     supra
    0.83
     holistic
    0.82
     universal
    0.82
     collegiate
    0.81
    Activations Density 0.345%

    No Known Activations