© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 20917
    Prev
    Next
    INDEX
    Explanations

    mentions of the Afghan political leader Hamid Karzai

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Hamid Karzai and related discussions about Afghanistan

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORT
    -0.68
     probable
    -0.68
    ezvous
    -0.65
    Mary
    -0.65
     BET
    -0.61
     latitude
    -0.58
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.57
     thief
    -0.57
     cryptic
    -0.56
    resp
    -0.56
    POSITIVE LOGITS
    zai
    1.67
    istani
    1.04
    gee
    0.94
    enei
    0.93
    gha
    0.89
    esi
    0.84
    zag
    0.82
    qi
    0.81
     Jinping
    0.81
    za
    0.80
    Activations Density 0.005%

    No Known Activations