© 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. 11-RES-JB
    11. 17348
    Prev
    Next
    INDEX
    Explanations

    words related to policies and changes in rules or regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to policy changes and regulations

    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
    ertodd
    -0.89
    aez
    -0.82
    emouth
    -0.81
    conom
    -0.80
    udi
    -0.73
    agues
    -0.70
    =]
    -0.70
    adows
    -0.69
    ARDIS
    -0.69
    iddles
    -0.68
    POSITIVE LOGITS
     guidelines
    1.52
     policy
    1.50
     policies
    1.44
     motto
    1.33
     rules
    1.27
     Guidelines
    1.26
     guideline
    1.24
     procedures
    1.23
     stance
    1.23
    iquette
    1.21
    Activations Density 0.425%

    No Known Activations