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. 3-RES-JB
    6. 836
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Metropolitan"

    oai_token-act-pair · gpt-3.5-turbo

    references to metropolitan areas and authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enes
    -0.85
    fty
    -0.81
    cius
    -0.78
    oward
    -0.74
    vg
    -0.71
    ften
    -0.69
    vous
    -0.69
    standing
    -0.69
    gotten
    -0.69
    \\\\\\\\
    -0.68
    POSITIVE LOGITS
    ropolitan
    1.04
     Metropolitan
    1.01
     Transportation
    0.89
     Borough
    0.88
     Mellon
    0.88
     Statistical
    0.86
     District
    0.83
     Improvement
    0.83
     EntityItem
    0.82
     Transit
    0.79
    Activations Density 0.004%

    No Known Activations