© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2519
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific political figure with the surname "Sarkozy"

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    mentions of the name "Sarkozy" and associated terms or phrases in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ocket
    -0.65
    ates
    -0.64
    ingly
    -0.61
    iture
    -0.60
    orah
    -0.58
     miscarriage
    -0.58
    atively
    -0.58
    brance
    -0.57
    piration
    -0.56
    aukee
    -0.56
    POSITIVE LOGITS
    inus
    0.65
    ¿
    0.63
    ovie
    0.60
    ius
    0.58
    ozy
    0.56
    ©¶æ
    0.56
    iban
    0.55
    ion
    0.55
    added
    0.54
    ivari
    0.54
    Activations Density 0.201%

    No Known Activations