© 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. 4-RES-JB
    11. 4790
    Prev
    Next
    INDEX
    Explanations

    references to countries or political figures, particularly focusing on Lithuania and Lavrov

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Lithuania and key figures associated with it, such as Luna and Lavrov

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

    No Comments

    Negative Logits
    structed
    -0.79
    illed
    -0.77
    ulating
    -0.74
    nels
    -0.74
    ulates
    -0.74
    ahon
    -0.74
    anked
    -0.71
    ulated
    -0.71
    querque
    -0.71
    insula
    -0.70
    POSITIVE LOGITS
     Luthor
    0.93
    uggage
    0.83
    yrics
    0.80
    ibrary
    0.80
    cius
    0.77
    ocate
    0.76
     Messi
    0.75
     Lamp
    0.75
    orem
    0.74
    uania
    0.73
    Activations Density 0.075%

    No Known Activations