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. 10-RES-JB
    6. 22939
    Prev
    Next
    INDEX
    Explanations

    phrases related to emergency evacuations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nan
    -0.78
    aque
    -0.77
    chery
    -0.72
    swick
    -0.70
    mbol
    -0.69
    Downloadha
    -0.68
    acca
    -0.67
    ourke
    -0.67
    cius
    -0.66
    kered
    -0.66
    POSITIVE LOGITS
     shelters
    0.80
     zones
    0.76
    uating
    0.75
     orders
    0.74
    ylum
    0.73
     evac
    0.72
    uations
    0.72
     evacuation
    0.71
     relocation
    0.70
     evacuate
    0.69
    Activations Density 0.084%

    No Known Activations