© 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. 9118
    Prev
    Next
    INDEX
    Explanations

    positive sentiments and expressions of appreciation

    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
    480
    +0.14
    0.6%
    397
    +0.11
    0.5%
    398
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    697
    +0.14
    0.05
    354
    +0.11
    0.06
    624
    +0.10
    0.04
    Negative Logits
     coerc
    -0.75
    toggle
    -0.72
     delinquent
    -0.70
     restraining
    -0.68
     prohibitions
    -0.65
     coercive
    -0.65
     vanish
    -0.65
     defaults
    -0.64
     vanishing
    -0.63
     Nope
    -0.63
    POSITIVE LOGITS
     thank
    1.23
     congratulate
    1.19
     congratulated
    1.12
     thanked
    1.10
     compliment
    1.09
     congr
    1.04
    Congratulations
    1.03
     congratulations
    1.02
     THANK
    1.00
     compliments
    0.98
    Activations Density 0.583%

    No Known Activations