© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 24391
    Prev
    Next
    INDEX
    Explanations

    mentions of congratulations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of congratulations and celebratory sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blacklist
    -0.80
     inconsist
    -0.77
     persecut
    -0.74
    rors
    -0.74
     prosecutions
    -0.73
    Viol
    -0.73
    Unless
    -0.72
    illegal
    -0.72
     bankrupt
    -0.71
    icides
    -0.71
    POSITIVE LOGITS
     congratulated
    1.53
     thanked
    1.43
     compliment
    1.35
     joked
    1.28
     hugged
    1.25
     cheered
    1.22
     exclaimed
    1.21
     congrat
    1.20
     applauded
    1.17
     thanking
    1.16
    Activations Density 0.627%

    No Known Activations