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

    Neuronpedia

    APICircuit 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. 24120
    Prev
    Next
    INDEX
    Explanations

    personal names and titles of political figures

    oai_token-act-pair · gpt-3.5-turbo

    names of political leaders and their associated activities or statements

    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
    DragonMagazine
    -0.85
     Memphis
    -0.73
     Hiroshima
    -0.72
     Wichita
    -0.71
     Tulsa
    -0.71
     USA
    -0.69
     Honolulu
    -0.68
     honor
    -0.66
    Miami
    -0.65
     Omaha
    -0.64
    POSITIVE LOGITS
     MPs
    1.03
     MLA
    0.96
     constituency
    0.90
     cabinet
    0.88
     Parliamentary
    0.87
     Opposition
    0.86
     Tories
    0.86
     Liberal
    0.85
     Liberals
    0.85
     parliamentary
    0.85
    Activations Density 0.311%

    No Known Activations