© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RES-JB
    11. 22335
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual, "Donald J. Trump."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Donald Trump

    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
    ulhu
    -0.72
    ife
    -0.66
     Worker
    -0.61
    oph
    -0.58
    é¾įå¥ij士
    -0.57
    staff
    -0.57
    reditary
    -0.57
     Tycoon
    -0.55
     Bengal
    -0.54
    ances
    -0.54
    POSITIVE LOGITS
    redits
    0.67
    thening
    0.58
    ermanent
    0.54
    ////
    0.53
     notice
    0.52
    nai
    0.52
    JV
    0.51
    dot
    0.51
     tacit
    0.50
     --------
    0.48
    Activations Density 0.168%

    No Known Activations