Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 10574
    Prev
    Next
    INDEX
    Explanations

    phrases related to emergency situations

    oai_token-act-pair · gpt-3.5-turbo

    references to emergency services and situations

    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
    hetti
    -0.80
    boa
    -0.79
    nan
    -0.74
    atell
    -0.74
    artisan
    -0.73
    kies
    -0.70
    tten
    -0.70
    orn
    -0.70
    emi
    -0.69
    eta
    -0.69
    POSITIVE LOGITS
     responders
    0.98
     contraception
    0.90
     evacuation
    0.89
     exits
    0.89
     room
    0.89
     response
    0.87
     situations
    0.85
    gency
    0.85
     rooms
    0.84
    aneously
    0.82
    Activations Density 0.060%

    No Known Activations