© 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. 11-RES-JB
    11. 196
    Prev
    Next
    INDEX
    Explanations

    objects commonly found in a kitchen or used for food preparation

    oai_token-act-pair · gpt-3.5-turbo

    references to containers and utensils used for food preparation or storage

    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
     Fighters
    -0.77
     Bonds
    -0.71
     UTC
    -0.70
     guiActiveUn
    -0.66
     Ath
    -0.64
    OTO
    -0.61
     Academy
    -0.59
     Lauder
    -0.58
    ETH
    -0.58
     IST
    -0.58
    POSITIVE LOGITS
     lid
    1.20
     filled
    1.15
     overflowing
    1.14
    ful
    1.14
     containing
    1.11
    pipe
    1.07
    gie
    1.04
    lain
    1.02
     emptied
    1.01
     contents
    0.95
    Activations Density 0.123%

    No Known Activations