© 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. 9-RES-JB
    11. 21555
    Prev
    Next
    INDEX
    Explanations

    keywords related to media content, news articles, and actions related to accountability

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to media, storytelling, and reporting

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    creen
    -0.76
     Caucus
    -0.73
    cium
    -0.67
     Mississ
    -0.67
    ystem
    -0.62
     Roads
    -0.62
     Lank
    -0.62
    âĦ¢
    -0.61
     Settlement
    -0.61
    ECD
    -0.61
    POSITIVE LOGITS
     wise
    1.03
    wise
    0.97
    lessly
    0.89
    ally
    0.87
    fully
    0.85
    ually
    0.82
    arily
    0.81
    ically
    0.81
    less
    0.75
     versa
    0.74
    Activations Density 0.407%

    No Known Activations