© 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. 11-RES-JB
    11. 3432
    Prev
    Next
    INDEX
    Explanations

    names related to Vasquez or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific names, particularly "Vasquez" and "Kas."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beaver
    -0.67
    ITED
    -0.62
     Drift
    -0.61
     Gregg
    -0.61
     Columb
    -0.60
     handle
    -0.59
     split
    -0.58
     Carnegie
    -0.57
     Cf
    -0.57
    OLOG
    -0.57
    POSITIVE LOGITS
    quez
    1.30
    sem
    1.15
    sel
    1.08
    chwitz
    1.07
    daq
    1.04
    imir
    1.01
    henko
    1.01
    sein
    1.00
    hiba
    1.00
    ily
    1.00
    Activations Density 0.053%

    No Known Activations