© 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. 13743
    Prev
    Next
    INDEX
    Explanations

    mentions of Russian names and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to Russian political figures and events

    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
     Cricket
    -0.93
     Rodney
    -0.92
    uckland
    -0.92
     Baylor
    -0.88
     Beckham
    -0.85
     Buffy
    -0.85
    querque
    -0.84
     cider
    -0.83
    Haw
    -0.83
     Tasman
    -0.82
    POSITIVE LOGITS
     Moscow
    2.35
     Kremlin
    2.35
     Putin
    2.31
    Moscow
    2.27
    Putin
    2.23
     Russian
    2.21
     Dmitry
    2.18
     Russia
    2.13
     Russians
    2.13
     Sergei
    2.09
    Activations Density 1.015%

    No Known Activations