© 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. 12-RES-JB
    11. 4151
    Prev
    Next
    INDEX
    Explanations

    names, specifically the name "John"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    the name "John" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     unilaterally
    -0.75
     haste
    -0.73
     warranted
    -0.70
     reverse
    -0.70
     unnecessary
    -0.69
     exagger
    -0.69
     necessary
    -0.66
     leap
    -0.65
     sweeping
    -0.65
     discretion
    -0.65
    POSITIVE LOGITS
    athan
    1.49
    nie
    1.27
    athon
    1.15
     Podesta
    1.03
    ston
    0.97
    etta
    0.95
     Doe
    0.91
     Sop
    0.87
     Cena
    0.86
    stone
    0.85
    Activations Density 0.016%

    No Known Activations