© 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. 11-RES-JB
    11. 20572
    Prev
    Next
    INDEX
    Explanations

    politicians' names

    oai_token-act-pair · gpt-3.5-turbo

    references to political candidates and their standings in elections

    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
    EMENT
    -0.59
    Gaza
    -0.57
     interacts
    -0.57
     forwarded
    -0.57
    ranging
    -0.56
    Maps
    -0.55
    kef
    -0.54
    ãĤ¬
    -0.53
     accessed
    -0.53
     Specific
    -0.52
    POSITIVE LOGITS
     in
    0.87
     by
    0.78
    aurus
    0.71
     altogether
    0.70
     athlet
    0.69
     decisively
    0.69
     atop
    0.68
    velt
    0.68
     anytime
    0.66
    oliath
    0.66
    Activations Density 0.395%

    No Known Activations