© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 24097
    Prev
    Next
    INDEX
    Explanations

    messages or statements expressing gratitude or condolences

    oai_token-act-pair · gpt-3.5-turbo

    phrases conveying expressions of gratitude and condolences

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     theoretically
    -0.71
    catch
    -0.68
    optional
    -0.68
     plaus
    -0.68
    iddle
    -0.68
     IQ
    -0.67
    iddling
    -0.66
     triv
    -0.66
    ?,
    -0.65
    ById
    -0.64
    POSITIVE LOGITS
     THANK
    1.43
     thank
    1.37
     condolences
    1.28
     Thank
    1.24
     congratulations
    1.23
     apologize
    1.23
    Thank
    1.21
     saddened
    1.21
     mourn
    1.20
     apologies
    1.20
    Activations Density 0.954%

    No Known Activations