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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 2791
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation or gratitude towards others

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and thankfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ģĸ
    -0.74
    xtap
    -0.66
     depending
    -0.64
    depending
    -0.60
    oiler
    -0.59
     blaming
    -0.58
     defaults
    -0.58
    ocide
    -0.58
    ģ«
    -0.57
     losers
    -0.57
    POSITIVE LOGITS
     courage
    0.79
     tirelessly
    0.78
     responsibly
    0.75
    !]
    0.75
     brave
    0.74
     generously
    0.74
     :)
    0.73
     yesterday
    0.68
     courageous
    0.67
     peacefully
    0.67
    Activations Density 0.181%

    No Known Activations