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. 11-RES-JB
    6. 18109
    Prev
    Next
    INDEX
    Explanations

    mentions of political leadership, particularly regarding the position of President of the United States

    oai_token-act-pair · gpt-3.5-turbo

    references to the presidency and the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     offerings
    -0.71
     gears
    -0.69
     volumes
    -0.68
     imports
    -0.68
     ramps
    -0.66
     storylines
    -0.66
     gaps
    -0.64
     injections
    -0.64
     scandals
    -0.62
     backlog
    -0.62
    POSITIVE LOGITS
     United
    1.35
    United
    1.25
     Republic
    1.20
     UNITED
    1.18
     Confederacy
    1.16
     Philippines
    1.03
     republic
    1.01
    çİĭ
    0.99
    Republic
    0.98
     Commonwealth
    0.97
    Activations Density 0.126%

    No Known Activations