© 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. 7140
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and organizations

    oai_token-act-pair · gpt-3.5-turbo
    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
     whisky
    -0.84
     shaving
    -0.79
    olkien
    -0.78
     Scotch
    -0.77
     shave
    -0.76
     frontier
    -0.75
     beard
    -0.75
     Yaz
    -0.75
    cig
    -0.73
    âĹ¼
    -0.73
    POSITIVE LOGITS
     DNC
    2.26
     Wasserman
    1.80
     Podesta
    1.60
     Debbie
    1.39
     Democratic
    1.30
     Donna
    1.29
    Democratic
    1.26
     RNC
    1.25
     Braz
    1.23
     Dems
    1.21
    Activations Density 0.235%

    No Known Activations