© 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. 9-RES-JB
    11. 18254
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly "Michele Bachmann" and other related names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eties
    -0.72
     vomit
    -0.72
    ially
    -0.69
     goodwill
    -0.67
    iating
    -0.63
     Jericho
    -0.62
     Kamp
    -0.62
    lies
    -0.61
     Dragonbound
    -0.60
     Riy
    -0.60
    POSITIVE LOGITS
    mann
    1.09
    ynski
    0.94
     Bach
    0.91
    nown
    0.86
    anski
    0.83
    pheus
    0.81
    ao
    0.78
    conservancy
    0.77
    anson
    0.76
    grain
    0.74
    Activations Density 0.078%

    No Known Activations