© 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. 7-RES-JB
    11. 1992
    Prev
    Next
    INDEX
    Explanations

    keywords related to political events and competitions

    oai_token-act-pair · gpt-3.5-turbo

    references to political events and locations, specifically elections and islands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ople
    -0.63
    bilt
    -0.63
     bases
    -0.61
    âĸ¬
    -0.60
    ience
    -0.59
    rious
    -0.59
    ctor
    -0.57
    staff
    -0.57
     Hancock
    -0.56
    OTS
    -0.56
    POSITIVE LOGITS
    creen
    1.52
    pace
    1.39
    hift
    1.35
    hips
    1.34
    pring
    1.32
    mith
    1.30
    chool
    1.29
    cale
    1.28
    cape
    1.24
    paces
    1.20
    Activations Density 0.176%

    No Known Activations