© 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. 12-RES-JB
    11. 4621
    Prev
    Next
    INDEX
    Explanations

    mentions of political actions and international relations, particularly related to sanctions against countries

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mentions of sanctions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ilar
    -0.82
    ĸļ
    -0.81
    ¥µ
    -0.79
    cellence
    -0.75
    ãĤ¦ãĤ¹
    -0.74
     Rebell
    -0.70
    icent
    -0.69
    ãĤ¤ãĥĪ
    -0.69
    ocent
    -0.68
     Noir
    -0.67
    POSITIVE LOGITS
     relief
    1.32
     levied
    1.29
     imposed
    1.29
     against
    1.12
     sanctions
    1.08
     regime
    1.07
     targeting
    1.06
     regimes
    1.06
     lifted
    1.00
    against
    0.99
    Activations Density 0.073%

    No Known Activations