© 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. 10-RES-JB
    11. 6221
    Prev
    Next
    INDEX
    Explanations

    terms related to molecular biology, including RNA types, proteins, barriers, and minerals

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of items or categories

    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
    jer
    -0.86
    edin
    -0.84
    nesday
    -0.80
    Gov
    -0.79
    Deal
    -0.78
    Town
    -0.77
    udence
    -0.77
    vc
    -0.75
    ruary
    -0.74
    Phone
    -0.74
    POSITIVE LOGITS
     types
    1.58
     organisms
    1.57
     species
    1.52
     substances
    1.49
     kinds
    1.42
     components
    1.37
     factors
    1.37
     enzymes
    1.35
     phenomena
    1.34
     forms
    1.31
    Activations Density 0.271%

    No Known Activations