© 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. 11-RES-JB
    11. 18725
    Prev
    Next
    INDEX
    Explanations

    years related to elections

    oai_token-act-pair · gpt-3.5-turbo

    references to specific election years and related political events

    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
    terday
    -0.78
    bags
    -0.71
     dated
    -0.69
     lately
    -0.68
    OSH
    -0.67
    attr
    -0.67
     tomorrow
    -0.67
     today
    -0.67
    chrome
    -0.65
    morrow
    -0.65
    POSITIVE LOGITS
     elections
    1.05
     election
    1.04
     Olympics
    1.03
     presidential
    1.01
     midterm
    0.98
     uprising
    0.98
     landslide
    0.92
     census
    0.92
     inauguration
    0.90
     tsunami
    0.89
    Activations Density 0.093%

    No Known Activations