© 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. 7-RES-JB
    11. 24068
    Prev
    Next
    INDEX
    Explanations

    the name "Mikhail" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those named Mikhail and Sergei

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bee
    -0.74
    roads
    -0.73
    gate
    -0.72
    Country
    -0.72
    shire
    -0.70
    Bee
    -0.68
    pled
    -0.66
    bury
    -0.66
     Episcopal
    -0.66
    Mother
    -0.66
    POSITIVE LOGITS
     Mikhail
    1.16
     Putin
    1.04
    achev
    1.03
     Dmitry
    1.03
    ovsky
    1.03
     Lavrov
    1.02
    ovych
    1.02
    ovich
    1.00
     Vlad
    0.96
    akov
    0.95
    Activations Density 0.058%

    No Known Activations