© 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. 11-RES-JB
    11. 5662
    Prev
    Next
    INDEX
    Explanations

    structures and materials that are strong or resilient

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to durability and resistance to damage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    iland
    -0.87
    oway
    -0.87
    LLOW
    -0.72
    oiler
    -0.70
     âľ
    -0.68
    ourced
    -0.68
    rone
    -0.67
    facts
    -0.66
    ãĤ¤ãĥĪ
    -0.66
    listed
    -0.66
    POSITIVE LOGITS
     sunlight
    1.17
     exposure
    1.17
     ingestion
    1.11
     friction
    1.07
     contact
    1.06
     rubbing
    1.04
     mishand
    1.03
     moisture
    1.03
     ultraviolet
    1.03
     bombardment
    1.03
    Activations Density 0.346%

    No Known Activations