© 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. 21735
    Prev
    Next
    INDEX
    Explanations

    conspiracy-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to conspiracy theories and associated organizations

    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
    vity
    -0.86
    ardy
    -0.85
     Towns
    -0.75
    uberty
    -0.70
    atoon
    -0.68
    ouple
    -0.68
     pauses
    -0.67
     anecd
    -0.66
     outdoors
    -0.66
    estyles
    -0.65
    POSITIVE LOGITS
     Rothschild
    1.47
     Illuminati
    1.45
     Soros
    1.37
    uminati
    1.32
     Zionist
    1.30
     disinformation
    1.29
     Satanic
    1.26
     cabal
    1.26
     CFR
    1.25
     CIA
    1.21
    Activations Density 0.926%

    No Known Activations