© 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. 10-RES-JB
    11. 18585
    Prev
    Next
    INDEX
    Explanations

    names of organizations and entities, specifically related to news and media

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent figures, companies, or brands

    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
    ĸļ
    -0.77
    rawdownloadcloneembedreportprint
    -0.72
    natureconservancy
    -0.62
    Interstitial
    -0.57
    xual
    -0.57
     Boko
    -0.56
    uyomi
    -0.55
     Pyr
    -0.53
     briefs
    -0.53
    enegger
    -0.53
    POSITIVE LOGITS
    ·
    0.72
    ĩ
    0.65
    «
    0.64
    intern
    0.62
    µ
    0.61
    ¹
    0.59
    ½
    0.59
    ³
    0.59
    é£
    0.57
    °
    0.57
    Activations Density 0.529%

    No Known Activations