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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 6636
    Prev
    Next
    INDEX
    Explanations

    references to Vice Presidents

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the title "Vice 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
    atta
    -0.74
    ach
    -0.67
     kidding
    -0.65
    doms
    -0.65
    lees
    -0.63
    ont
    -0.62
     phyl
    -0.62
    sett
    -0.61
    yson
    -0.60
    kit
    -0.60
    POSITIVE LOGITS
     Vice
    3.83
    Vice
    3.12
     vice
    2.46
     VP
    1.94
     VICE
    1.80
     Deputy
    1.52
    vice
    1.50
     President
    1.50
     Biden
    1.36
    President
    1.29
    Activations Density 0.009%

    No Known Activations