© 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. 2-RES-JB
    11. 18576
    Prev
    Next
    INDEX
    Explanations

    phrases related to the POTUS (President of the United States) and Melania Trump

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the political figure "OTUS" (often referencing the President) and the First Lady Melania Trump

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     à¨
    -0.69
     Esk
    -0.67
     gou
    -0.67
     pubs
    -0.63
    uns
    -0.63
    bor
    -0.62
    gered
    -0.62
    uld
    -0.62
     semi
    -0.61
     kindred
    -0.61
    POSITIVE LOGITS
    OTUS
    1.60
    hower
    0.86
     TRUMP
    0.83
    ervative
    0.81
    stakes
    0.80
     Jinping
    0.80
    blog
    0.76
    ierrez
    0.75
    ipop
    0.73
    trump
    0.72
    Activations Density 0.005%

    No Known Activations