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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6487
    Prev
    Next
    INDEX
    Explanations

    phone numbers to call for emergencies

    oai_token-act-pair · gpt-3.5-turbo

    instances of the emergency phone number "911" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wikipedia
    -0.89
    secut
    -0.77
    protein
    -0.76
    thumbnails
    -0.74
    xtap
    -0.70
    hend
    -0.70
    chin
    -0.70
    lists
    -0.70
    lihood
    -0.70
    glomer
    -0.67
    POSITIVE LOGITS
     911
    1.17
     dispatcher
    1.00
    gencies
    0.82
    ILLE
    0.80
     emergencies
    0.78
     hotline
    0.76
     caller
    0.71
     emergency
    0.70
     microphones
    0.69
    Emergency
    0.69
    Activations Density 0.027%

    No Known Activations