© 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. 9-RES-JB
    11. 4185
    Prev
    Next
    INDEX
    Explanations

    phrases related to various types of debts and financial instruments

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with loans, drugs, and various forms of media consumption

    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
    »Ĵ
    -0.87
    epad
    -0.82
    omething
    -0.81
    romeda
    -0.80
    etheless
    -0.79
    cale
    -0.78
    pite
    -0.78
    estamp
    -0.77
    Ļ½
    -0.73
    heet
    -0.72
    POSITIVE LOGITS
     owners
    1.07
     holders
    1.06
     registrations
    1.04
     makers
    1.01
     sizes
    0.99
     rentals
    0.99
     replacements
    0.98
     shipments
    0.97
    holders
    0.96
     manufacturers
    0.95
    Activations Density 0.620%

    No Known Activations