© 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. 10405
    Prev
    Next
    INDEX
    Explanations

    organizations or groups related to political activism and advocacy

    oai_token-act-pair · gpt-3.5-turbo

    references to political organizations and movements

    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
     simulator
    -0.80
     wallpaper
    -0.80
     waters
    -0.76
     bog
    -0.75
     jargon
    -0.74
     tongue
    -0.74
     catalogue
    -0.74
     dessert
    -0.73
     ruler
    -0.73
     licence
    -0.73
    POSITIVE LOGITS
    PAC
    1.20
     Coalition
    1.20
    Vote
    1.18
    Choice
    1.17
     Equality
    1.15
     Majority
    1.15
     Voters
    1.12
     Matters
    1.09
     Against
    1.09
    Freedom
    1.09
    Activations Density 0.281%

    No Known Activations