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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18822
    Prev
    Next
    INDEX
    Explanations

    terms related to political and governmental contexts, specifically concerning certain countries or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific abbreviations or terms related to organizations or entities

    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
     twe
    -0.63
    assetsadobe
    -0.60
     tart
    -0.59
     Led
    -0.59
     cz
    -0.59
     Hampton
    -0.57
    phe
    -0.56
     dish
    -0.56
    dq
    -0.55
     Cooke
    -0.55
    POSITIVE LOGITS
    uni
    0.87
    uthor
    0.85
    ĨĴ
    0.81
    ña
    0.79
    ģ«
    0.79
    ¦
    0.77
    Boot
    0.73
    boot
    0.73
    ugi
    0.72
    arthed
    0.71
    Activations Density 0.078%

    No Known Activations