© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 22260
    Prev
    Next
    INDEX
    Explanations

    words related to protective headgear, especially "helmet"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of helmets and related protective gear

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     XY
    -0.74
    lishes
    -0.71
    estate
    -0.69
    RAW
    -0.67
     Freed
    -0.66
     Wim
    -0.65
    dates
    -0.65
     Rowling
    -0.64
     Fundamental
    -0.64
    ouk
    -0.64
    POSITIVE LOGITS
     helmet
    3.71
     helmets
    3.17
     Helmet
    2.92
     Helm
    1.78
     goggles
    1.67
     headset
    1.56
     gloves
    1.46
     skull
    1.43
     mask
    1.40
     helm
    1.37
    Activations Density 0.018%

    No Known Activations