© 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 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. 4-RES-JB
    11. 6980
    Prev
    Next
    INDEX
    Explanations

    references to political terms such as "term" and "election."

    oai_token-act-pair · gpt-3.5-turbo

    references to political terms and elected positions

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

    No Comments

    Negative Logits
    ICLE
    -0.76
     Klu
    -0.73
    ergic
    -0.70
     Cosponsors
    -0.70
    NetMessage
    -0.64
    UCT
    -0.64
    OWN
    -0.64
     istg
    -0.63
     Unic
    -0.63
    chy
    -0.63
    POSITIVE LOGITS
    mate
    0.88
    ability
    0.87
    abilities
    0.83
    acity
    0.81
    interstitial
    0.81
    term
    0.80
    cap
    0.77
    Term
    0.74
    timer
    0.74
     mate
    0.73
    Activations Density 0.014%

    No Known Activations