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. 22292
    Prev
    Next
    INDEX
    Explanations

    words related to political processes, such as "Cabinet," "elections," and "Senate" in the context of government activities

    oai_token-act-pair · gpt-3.5-turbo

    references to political decisions and positions

    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
     DRM
    -0.78
     MDMA
    -0.75
     cig
    -0.73
    Maps
    -0.72
     warehouses
    -0.70
    lag
    -0.69
     MPEG
    -0.68
     Customers
    -0.67
     Crate
    -0.66
     shoppers
    -0.66
    POSITIVE LOGITS
     appointing
    1.58
     nomination
    1.51
     appoint
    1.51
     nominating
    1.50
     nominate
    1.48
     nominations
    1.46
     appointment
    1.34
     appointed
    1.30
     nominees
    1.29
     nominated
    1.29
    Activations Density 0.657%

    No Known Activations