© 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. 10-RES-JB
    11. 5768
    Prev
    Next
    INDEX
    Explanations

    information related to connections and ties between individuals or entities, particularly when it involves Russia

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating connections or ties between individuals and entities, particularly involving political figures and foreign influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meal
    -0.84
    bra
    -0.84
    ItemThumbnailImage
    -0.82
    reci
    -0.82
    ciation
    -0.79
     partName
    -0.78
    anguage
    -0.78
    existence
    -0.76
    morrow
    -0.76
    ipeg
    -0.76
    POSITIVE LOGITS
     lobbyists
    1.14
     WikiLeaks
    1.11
     Wikileaks
    1.09
     shadowy
    1.08
     disgr
    1.08
     Kremlin
    1.08
     dictators
    1.07
     shady
    1.03
     billionaire
    1.02
     smugglers
    1.02
    Activations Density 0.234%

    No Known Activations