© 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 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. 10-RES-JB
    11. 3498
    Prev
    Next
    INDEX
    Explanations

    medical conditions and harmful substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to chemicals and their impacts on health and the environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.81
     Cosponsors
    -0.68
    xon
    -0.68
     VIDEOS
    -0.67
     showc
    -0.66
     Transcript
    -0.62
    nir
    -0.62
    Textures
    -0.62
     ç¥ŀ
    -0.62
    taboola
    -0.61
    POSITIVE LOGITS
     designed
    1.18
     consisting
    1.06
     whose
    1.03
     invented
    1.02
     comprised
    1.02
     devised
    1.01
     meant
    0.98
     conceived
    0.94
     created
    0.94
     synonymous
    0.90
    Activations Density 0.322%

    No Known Activations