© 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. 8-RES-JB
    11. 6975
    Prev
    Next
    INDEX
    Explanations

    phrases related to policies or programs, especially those involving specific actions for the benefit of children

    oai_token-act-pair · gpt-3.5-turbo

    references to government policies and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     brim
    -1.00
     tart
    -0.74
     capsule
    -0.74
    loe
    -0.71
     scrim
    -0.70
     dreams
    -0.70
     jelly
    -0.70
    rss
    -0.70
    natureconservancy
    -0.70
     haunt
    -0.68
    POSITIVE LOGITS
     Nations
    0.81
     Devices
    0.79
     Practices
    0.77
     Intervention
    0.76
    ÙĬ
    0.76
     Reporting
    0.75
     Prevention
    0.75
     Skies
    0.74
    Ĥª
    0.73
    س
    0.72
    Activations Density 0.190%

    No Known Activations