© 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. 8-RES-JB
    11. 6938
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or acknowledgments

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express gratitude or thankfulness for contributions or assistance

    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
    soever
    -0.80
    heid
    -0.74
    lol
    -0.73
    Posts
    -0.72
    conn
    -0.69
    Sym
    -0.66
    Fr
    -0.65
    demand
    -0.65
    LAB
    -0.65
    deb
    -0.64
    POSITIVE LOGITS
     sponsoring
    0.83
     inspiration
    0.82
    gery
    0.82
    geries
    0.81
     whom
    0.78
     instance
    0.78
     powering
    0.76
     hosting
    0.74
     example
    0.73
    ked
    0.73
    Activations Density 0.128%

    No Known Activations