© 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. 9-RES-JB
    11. 15599
    Prev
    Next
    INDEX
    Explanations

    organizations or associations, including names and affiliations

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and associations involved in animal welfare and environmental conservation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    always
    -0.80
     spo
    -0.80
     tricks
    -0.78
     grabs
    -0.75
     fuck
    -0.75
     sauce
    -0.73
     overpowered
    -0.72
    bender
    -0.72
    chu
    -0.72
     betray
    -0.72
    POSITIVE LOGITS
     University
    1.27
     Institute
    1.20
     Carnegie
    1.20
     Federation
    1.18
     Instit
    1.17
     Municipal
    1.17
     Heritage
    1.17
     Universities
    1.17
     Educational
    1.16
     Colleg
    1.15
    Activations Density 0.386%

    No Known Activations