© 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. 11-RES-JB
    11. 7056
    Prev
    Next
    INDEX
    Explanations

    proper nouns specifically related to a person with the name "Duncan."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Duncan"

    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
     attachments
    -0.64
     Rated
    -0.63
     passionate
    -0.61
     simulator
    -0.60
     false
    -0.59
     pains
    -0.59
     worthwhile
    -0.58
     ASA
    -0.58
    OHN
    -0.57
     justified
    -0.56
    POSITIVE LOGITS
    lap
    1.26
    edin
    1.25
    geons
    1.21
    geon
    1.13
    ning
    1.11
    wich
    1.05
    gey
    1.02
    sworth
    1.01
    nel
    1.01
    cair
    1.00
    Activations Density 0.034%

    No Known Activations