© 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. 0-RES-JB
    11. 23359
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and kindness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and kindness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contested
    -0.72
    scene
    -0.69
     competing
    -0.68
     SUP
    -0.68
     charged
    -0.67
    NC
    -0.65
    wang
    -0.64
    viks
    -0.64
    merce
    -0.64
    uter
    -0.64
    POSITIVE LOGITS
     gratitude
    2.32
     kindness
    2.28
     generosity
    2.20
     curiosity
    2.17
     humility
    2.11
     empathy
    1.95
     cynicism
    1.91
     optimism
    1.88
     honesty
    1.85
     arrogance
    1.84
    Activations Density 0.051%

    No Known Activations