© 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. 13749
    Prev
    Next
    INDEX
    Explanations

    names of people, specifically those named Chuck

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Chuck"

    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
    omorphic
    -0.71
     simultane
    -0.66
     anten
    -0.63
    worldly
    -0.62
    ODUCT
    -0.59
    */(
    -0.59
     concentration
    -0.59
     comparison
    -0.59
     glands
    -0.58
    kj
    -0.57
    POSITIVE LOGITS
    anut
    1.14
     Norris
    1.07
    wagon
    1.00
     Schumer
    1.00
     Grassley
    0.96
    bowl
    0.95
     Wend
    0.86
     Hag
    0.83
     Berry
    0.82
    ernaut
    0.80
    Activations Density 0.020%

    No Known Activations