© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12944
    Prev
    Next
    INDEX
    Explanations

    terms related to lobbying or advocating for specific causes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to lobbying and advocacy efforts

    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
    plet
    -0.69
    å°Ĩ
    -0.66
    miah
    -0.66
     ILCS
    -0.65
    psons
    -0.65
    ascript
    -0.64
    ãĥĻ
    -0.63
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.62
    ensional
    -0.61
    eye
    -0.61
    POSITIVE LOGITS
     tirelessly
    1.28
     against
    1.26
     unsuccessfully
    1.16
     for
    1.12
     passionately
    1.05
     vigorously
    1.05
     aggressively
    1.01
     loudly
    0.95
     extensively
    0.94
     forcefully
    0.94
    Activations Density 0.134%

    No Known Activations