© 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 EvalsExportsinterp-engineNEWAPI 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. 13755
    Prev
    Next
    INDEX
    Explanations

    phrases related to conspiracy theories

    oai_token-act-pair · gpt-3.5-turbo

    references to notable figures and institutions associated with conspiracy theories and skepticism

    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
     glim
    -0.94
     transition
    -0.83
     workspace
    -0.83
     quir
    -0.82
    ŃĶ
    -0.81
     weights
    -0.80
     defe
    -0.79
     satell
    -0.78
     transitions
    -0.78
     separ
    -0.77
    POSITIVE LOGITS
     Worse
    1.49
     Needless
    1.48
     Ironically
    1.39
     Apparently
    1.35
     Sadly
    1.30
     Meanwhile
    1.30
     Somehow
    1.29
     Shame
    1.26
     Surely
    1.24
     Whilst
    1.24
    Activations Density 0.596%

    No Known Activations