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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 19200
    Prev
    Next
    INDEX
    Explanations

    references to "Metropolitan" locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Metropolitan" in various contexts

    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
    fty
    -0.89
    cius
    -0.80
    \\\\\\\\
    -0.78
    kick
    -0.73
    pport
    -0.73
    standing
    -0.72
    verted
    -0.72
    enes
    -0.72
    hops
    -0.71
    vous
    -0.71
    POSITIVE LOGITS
    ropolitan
    1.04
     Metropolitan
    0.97
     Statistical
    0.94
     Borough
    0.94
     Transportation
    0.86
     Transit
    0.82
     District
    0.80
     Improvement
    0.80
     Police
    0.80
     Area
    0.78
    Activations Density 0.007%

    No Known Activations