© 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. 1-RES-JB
    11. 7676
    Prev
    Next
    INDEX
    Explanations

    mentions of items being physically worn by individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "worn"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reme
    -0.84
    aminer
    -0.73
    ommod
    -0.73
    ":["
    -0.71
    article
    -0.70
     slam
    -0.69
    square
    -0.65
    HER
    -0.64
    errilla
    -0.62
     Chomsky
    -0.62
    POSITIVE LOGITS
     worn
    1.55
    nesday
    0.99
     captcha
    0.96
     sleeves
    0.94
    worn
    0.92
     tiss
    0.86
     wearable
    0.85
     wear
    0.82
     jerseys
    0.81
     wore
    0.81
    Activations Density 0.008%

    No Known Activations