© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 13979
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and their campaigns, particularly focusing on comparisons and support levels

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their associated campaigns

    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
    hyde
    -0.81
    holes
    -0.78
    atos
    -0.78
    Tang
    -0.76
    adobe
    -0.75
    Trigger
    -0.73
    Downloadha
    -0.73
    rences
    -0.72
    Ĥª
    -0.70
    CHAPTER
    -0.70
    POSITIVE LOGITS
     candidacy
    1.45
     nomination
    1.27
     campaign
    1.27
     aides
    1.24
     presidential
    1.22
     reelection
    1.21
     advisers
    1.20
     detractors
    1.16
     opponents
    1.16
     opponent
    1.15
    Activations Density 0.232%

    No Known Activations