Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7265
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures, specifically presidents

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "President"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grind
    -0.69
     scrape
    -0.66
     esc
    -0.64
     QC
    -0.63
     Gy
    -0.62
     secondary
    -0.62
     eyeb
    -0.62
     Ib
    -0.62
     litter
    -0.62
     shift
    -0.60
    POSITIVE LOGITS
    President
    3.62
    president
    2.53
     President
    2.23
    Secretary
    2.05
     PRESIDENT
    2.04
     Presidents
    1.91
    Obama
    1.80
     president
    1.79
    Vice
    1.76
    Senator
    1.74
    Activations Density 0.013%

    No Known Activations