© 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. 12400
    Prev
    Next
    INDEX
    Explanations

    information related to various countries and research activities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic regions, countries, or entities involved in research or public health

    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
    venge
    -0.86
    ihad
    -0.83
    vana
    -0.80
    ontent
    -0.78
    abilia
    -0.78
    ibur
    -0.76
    livious
    -0.72
    iddler
    -0.72
    ooter
    -0.72
    aminer
    -0.71
    POSITIVE LOGITS
     Scientific
    0.83
     Geological
    0.79
     Medline
    0.78
     FDA
    0.77
     standardized
    0.76
     researchers
    0.75
     Geographic
    0.74
     Natural
    0.74
     laboratories
    0.74
     Folk
    0.74
    Activations Density 0.547%

    No Known Activations