© 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. 10-RES-JB
    11. 12807
    Prev
    Next
    INDEX
    Explanations

    References to "Presidents" and "Vice Presidents" with particular emphasis on "Joe" Biden and "Mike" Pence

    oai_token-act-pair · gpt-3.5-turbo

    references to vice presidents and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LESS
    -0.61
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.60
     cows
    -0.59
    é¾
    -0.59
    Score
    -0.58
    SK
    -0.55
    Thousands
    -0.55
     pest
    -0.54
    eros
    -0.54
    STER
    -0.54
    POSITIVE LOGITS
     Biden
    1.14
     Cheney
    0.90
    OTUS
    0.88
     Pence
    0.77
     Rahul
    0.76
    ial
    0.76
     Joe
    0.75
     Gore
    0.73
    owitz
    0.71
     Mike
    0.71
    Activations Density 0.031%

    No Known Activations