© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4072
    Prev
    Next
    INDEX
    Explanations

    concepts related to economics, policy, and societal disparities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to societal needs and disparities affecting different populations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥ³
    -0.69
    pty
    -0.68
    000000
    -0.66
    66666666
    -0.64
    ela
    -0.63
    ellow
    -0.62
    pload
    -0.61
    ilan
    -0.61
    0000000000000000
    -0.57
    raid
    -0.56
    POSITIVE LOGITS
     most
    1.90
     hardest
    1.88
     heaviest
    1.82
     strongest
    1.78
     greatest
    1.77
     least
    1.77
     longest
    1.73
     quickest
    1.70
     happiest
    1.70
     fastest
    1.69
    Activations Density 0.734%

    No Known Activations