© 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 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. 3413
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various people, places, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to people, places, and organizations

    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
     Pigs
    -0.72
    incarn
    -0.69
    Interested
    -0.64
    Ĭ±
    -0.62
    icol
    -0.62
    actionDate
    -0.60
    ploma
    -0.58
    cise
    -0.58
     Shutterstock
    -0.57
    geries
    -0.57
    POSITIVE LOGITS
     nevertheless
    1.11
     nonetheless
    0.98
     opted
    0.97
     resorted
    0.97
     must
    0.87
     reverted
    0.86
     ensured
    0.85
     seems
    0.83
     appears
    0.82
     decided
    0.82
    Activations Density 0.667%

    No Known Activations