© 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. 20969
    Prev
    Next
    INDEX
    Explanations

    names or references related to political figures named Lincoln

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Lincoln" in various contexts

    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
    hift
    -0.76
    Org
    -0.70
    ++++++++++++++++
    -0.63
     disadvant
    -0.63
     Flavoring
    -0.62
     Typhoon
    -0.60
     compan
    -0.60
     laun
    -0.60
    λ
    -0.60
     precip
    -0.60
    POSITIVE LOGITS
    shire
    1.86
     Lincoln
    0.80
    hurst
    0.80
    hower
    0.79
    ston
    0.79
    sworth
    0.77
    thal
    0.75
    beck
    0.75
    stones
    0.72
     Continental
    0.72
    Activations Density 0.060%

    No Known Activations