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. 10-RES-JB
    6. 22312
    Prev
    Next
    INDEX
    Explanations

    phrases related to political leaders, specifically chancellors, especially Chancellor Angela Merkel

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political figures, specifically chancellors

    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
    atoon
    -0.72
    ities
    -0.71
    ibaba
    -0.71
    Americans
    -0.71
     Navajo
    -0.70
    avez
    -0.69
    atown
    -0.64
    cells
    -0.63
    kinson
    -0.63
    nesota
    -0.63
    POSITIVE LOGITS
    llor
    1.43
     Chancellor
    1.20
     chancellor
    1.10
     Angela
    1.07
     Merkel
    1.03
    Chance
    0.77
    idge
    0.72
     emer
    0.68
    inator
    0.66
     Pell
    0.65
    Activations Density 0.022%

    No Known Activations