© 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. 20912
    Prev
    Next
    INDEX
    Explanations

    words related to conspiracy theories

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "ho" used in different contexts

    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
     mileage
    -0.70
     GOODMAN
    -0.66
     pathway
    -0.65
    CLASSIFIED
    -0.63
     pathways
    -0.63
    rations
    -0.63
    20439
    -0.63
     nucleus
    -0.62
     CPC
    -0.60
    course
    -0.60
    POSITIVE LOGITS
    arding
    1.33
    pper
    1.29
    ppy
    1.27
    ogle
    1.20
    oper
    1.18
    ppe
    1.17
    arse
    1.14
    ppers
    1.13
    pping
    1.12
    ofer
    1.10
    Activations Density 0.030%

    No Known Activations