© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 4975
    Prev
    Next
    INDEX
    Explanations

    phrases related to ethical considerations in software development and technology

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    concepts related to ethical considerations and decision-making in technology and programming

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Lyndon
    -0.79
     Carter
    -0.77
     Newark
    -0.74
     Bush
    -0.74
     Strauss
    -0.73
     Adolf
    -0.72
     Powell
    -0.70
     Franklin
    -0.70
     Roosevelt
    -0.69
     Trent
    -0.69
    POSITIVE LOGITS
    benefit
    0.98
     behavi
    0.93
     assumptions
    0.92
     considerations
    0.92
     variables
    0.91
     caveats
    0.91
     constraints
    0.90
     warranties
    0.90
     risks
    0.88
     risk
    0.87
    Activations Density 0.741%

    No Known Activations