© 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. 17367
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and 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
    640
    +0.20
    0.9%
    679
    +0.12
    0.6%
    16
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.20
    0.11
    640
    +0.12
    0.09
    679
    +0.11
    0.09
    Negative Logits
     displacement
    -0.75
     unatt
    -0.71
     overt
    -0.69
     submerged
    -0.69
     antit
    -0.68
     tack
    -0.68
     opponent
    -0.67
     enrol
    -0.66
     intercept
    -0.66
     temperament
    -0.66
    POSITIVE LOGITS
     Please
    1.54
     THANK
    1.50
     Hopefully
    1.46
     Thank
    1.45
     Thanks
    1.43
     :)
    1.39
     ðŁĻĤ
    1.36
     ;)
    1.28
     Congratulations
    1.27
     Firstly
    1.26
    Activations Density 0.384%

    No Known Activations