© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 13044
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between individuals and groups, particularly related to politics and investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to political investigations and connections involving Russia and the Trump campaign

    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
    liga
    -0.80
    FIELD
    -0.77
    SPONSORED
    -0.73
    Market
    -0.73
    CTV
    -0.72
    oka
    -0.72
     borne
    -0.69
    etically
    -0.67
    NetMessage
    -0.67
    essional
    -0.67
    POSITIVE LOGITS
     Clintons
    1.32
     Oval
    1.26
     FBI
    1.24
     president
    1.24
     White
    1.18
     bureau
    1.15
     Russians
    1.13
     Justice
    1.09
     CIA
    1.07
     Kremlin
    1.06
    Activations Density 0.206%

    No Known Activations