© 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. 3886
    Prev
    Next
    INDEX
    Explanations

    mentions of the political figure "Stephen Harper."

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

    mentions of the name "Stephen."

    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
    ividual
    -0.85
    DragonMagazine
    -0.85
    ktop
    -0.77
    */(
    -0.72
    icter
    -0.70
    theless
    -0.67
    ueless
    -0.64
    ãĤ¨ãĥ«
    -0.63
    eways
    -0.62
    xual
    -0.62
    POSITIVE LOGITS
     Harper
    0.98
     Porter
    0.80
     Lawson
    0.69
     Pearson
    0.65
     Con
    0.64
     Mc
    0.62
     Pol
    0.62
     Pont
    0.61
     Mand
    0.60
     Franks
    0.59
    Activations Density 0.013%

    No Known Activations