© 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. 3021
    Prev
    Next
    INDEX
    Explanations

    references to the word "helmet."

    oai_token-act-pair · gpt-3.5-turbo

    references to helmets and headgear

    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
     Restaur
    -0.80
    angu
    -0.80
    atoes
    -0.79
    icult
    -0.76
    iculture
    -0.73
    iculty
    -0.70
    quart
    -0.70
    inity
    -0.68
    uality
    -0.66
    atra
    -0.66
    POSITIVE LOGITS
     wearer
    1.19
     goggles
    1.12
     worn
    1.06
     headset
    0.98
     equipped
    0.97
     headsets
    0.96
     fitted
    0.87
     straps
    0.84
     helmets
    0.83
     headphones
    0.82
    Activations Density 0.070%

    No Known Activations