© 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. 22669
    Prev
    Next
    INDEX
    Explanations

    instances of the word "compared" and its variations in context relating to evaluations or contrasts

    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
    438
    +0.11
    0.5%
    94
    +0.11
    0.5%
    679
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.11
    0.02
    131
    +0.11
    0.02
    94
    +0.10
    0.02
    Negative Logits
    OTA
    -0.66
    authorized
    -0.62
     Robotics
    -0.59
     motors
    -0.58
     Polo
    -0.58
    atom
    -0.56
     Epidem
    -0.56
    PU
    -0.55
    allo
    -0.54
     Semin
    -0.54
    POSITIVE LOGITS
     favorably
    0.90
    icut
    0.75
    lihood
    0.73
     disadvant
    0.69
     Compare
    0.67
    ileaks
    0.66
    bryce
    0.65
    ivalent
    0.65
    illac
    0.65
    aneously
    0.64
    Activations Density 0.014%

    No Known Activations