© 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. 3250
    Prev
    Next
    INDEX
    Explanations

    dates, names, and locations in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    specific references to dates and names

    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
     CIS
    -0.89
     Syd
    -0.87
     Cec
    -0.87
     McKenzie
    -0.86
     Kad
    -0.86
     McM
    -0.85
     McKenna
    -0.83
     NIC
    -0.83
     Nek
    -0.80
     TM
    -0.80
    POSITIVE LOGITS
     Franklin
    1.19
    letters
    1.07
    quickShipAvailable
    1.00
    Letter
    0.99
     letter
    0.96
     Letters
    0.96
     Letter
    0.95
    letter
    0.94
     amendment
    0.87
     Hur
    0.87
    Activations Density 0.355%

    No Known Activations