© 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. 7-RES-JB
    11. 22891
    Prev
    Next
    INDEX
    Explanations

    actions related to preventive measures

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to prevention and safety measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iked
    -0.72
    alam
    -0.71
    unny
    -0.71
    amic
    -0.70
    bell
    -0.70
    ãģ®
    -0.66
    wikipedia
    -0.63
    ohm
    -0.62
    mar
    -0.62
    wrote
    -0.61
    POSITIVE LOGITS
     redundancy
    0.82
     comparisons
    0.78
     claimants
    0.76
     adherence
    0.73
     confusion
    0.72
     situations
    0.72
     compliance
    0.72
     detection
    0.70
     consistency
    0.70
     compatibility
    0.70
    Activations Density 0.209%

    No Known Activations