© 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. 6-RES-JB
    11. 14624
    Prev
    Next
    INDEX
    Explanations

    technology-related terms and companies

    oai_token-act-pair · gpt-3.5-turbo

    references to companies, organizations, or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ensional
    -0.65
    ourning
    -0.61
    depending
    -0.60
    jriwal
    -0.57
    ~~~~~~~~~~~~~~~~
    -0.57
     sloppy
    -0.56
     deduct
    -0.56
    ependent
    -0.56
    iblical
    -0.54
    yright
    -0.54
    POSITIVE LOGITS
    ).[
    0.76
    ®,
    0.73
     Ltd
    0.70
    hof
    0.67
    ).
    0.65
    *.
    0.65
    Us
    0.64
    âĦ¢
    0.61
    naire
    0.61
     ("
    0.61
    Activations Density 0.561%

    No Known Activations