© 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. 5241
    Prev
    Next
    INDEX
    Explanations

    political and governmental terms within texts

    oai_token-act-pair · gpt-3.5-turbo
    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
    ãĤ©
    -0.80
    ãĤ¨ãĥ«
    -0.78
    agin
    -0.78
    ãĤ£
    -0.76
    ":"/
    -0.73
    ãĤ§
    -0.72
    ãģł
    -0.70
    ebra
    -0.70
    viation
    -0.70
    EngineDebug
    -0.68
    POSITIVE LOGITS
     however
    0.90
     which
    0.87
     lawmakers
    0.87
     officials
    0.85
     authorities
    0.82
     including
    0.81
     prosecutors
    0.79
     legislators
    0.79
     policymakers
    0.78
     namely
    0.77
    Activations Density 0.212%

    No Known Activations