© 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. 20917
    Prev
    Next
    INDEX
    Explanations

    phrases related to individuals with the title "Dr."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals with the title "Dr."

    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
    LOAD
    -0.70
     goodbye
    -0.67
     defence
    -0.59
     compliment
    -0.58
     homeland
    -0.57
     layer
    -0.56
     Nato
    -0.56
     controllers
    -0.56
     quo
    -0.56
     coupling
    -0.56
    POSITIVE LOGITS
    udge
    1.17
    inks
    1.13
    ifting
    1.09
    inker
    1.09
    acon
    1.07
    agan
    1.06
    astically
    1.06
    ago
    1.03
    unks
    1.03
    iggs
    1.02
    Activations Density 0.024%

    No Known Activations