© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 1137
    Prev
    Next
    INDEX
    Explanations

    words related to gratitude and well-wishing

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and congratulatory messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    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

    Negative Logits
    apeshifter
    -0.80
    toggle
    -0.73
    ewitness
    -0.71
    agin
    -0.69
    umin
    -0.67
    rams
    -0.66
    rones
    -0.66
    oggle
    -0.66
    lishes
    -0.65
     telev
    -0.65
    POSITIVE LOGITS
     Thank
    1.09
     THANK
    1.03
     thank
    1.03
     Congratulations
    1.02
     Merry
    1.01
     congratulations
    0.99
    Thank
    0.97
    Congratulations
    0.96
     congr
    0.95
     Thanks
    0.91
    Activations Density 0.328%

    No Known Activations