© 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. 14619
    Prev
    Next
    INDEX
    Explanations

    medical terms and objective terms related to data and research

    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
    679
    +0.10
    0.4%
    715
    +0.09
    0.4%
    155
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    688
    +0.10
    0.01
    634
    +0.09
    0.01
    288
    +0.09
    0.01
    Negative Logits
    letters
    -0.89
    bowl
    -0.86
     Tycoon
    -0.86
    buck
    -0.84
    corn
    -0.84
    bird
    -0.83
    birds
    -0.81
    rooms
    -0.81
    pox
    -0.81
    Lago
    -0.80
    POSITIVE LOGITS
     appraisal
    0.91
     pronoun
    0.90
     observer
    0.90
     Objective
    0.89
    ives
    0.84
     criteria
    0.83
     evaluation
    0.83
     guiActiveUn
    0.82
     objective
    0.82
    ignty
    0.81
    Activations Density 0.021%

    No Known Activations