© 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. 0-RES-JB
    11. 8261
    Prev
    Next
    INDEX
    Explanations

    phrases related to conspiracy theories

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with conspiracy theories and conspiratorial thinking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Steal
    -0.72
     Grade
    -0.70
    otive
    -0.66
     Lay
    -0.65
     Peel
    -0.64
    chuk
    -0.63
     Presence
    -0.62
    ONEY
    -0.62
     Bridges
    -0.62
     Hig
    -0.60
    POSITIVE LOGITS
    atorial
    3.50
    icion
    1.95
    unn
    1.32
    ilateral
    1.19
    eah
    0.86
     Whedon
    0.85
     pollen
    0.84
    sonian
    0.84
     literal
    0.83
     sidel
    0.80
    Activations Density 0.018%

    No Known Activations