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. 4-RES-JB
    6. 5381
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "Heathrow."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Heathrow" and related references within the context of discussions

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

    No Comments

    Negative Logits
    ãĥ£
    -0.80
    uyomi
    -0.76
    resents
    -0.75
    acters
    -0.74
    afort
    -0.74
    essee
    -0.72
    ebus
    -0.72
    awaru
    -0.71
    edo
    -0.69
     tense
    -0.66
    POSITIVE LOGITS
    brook
    0.90
    mare
    0.89
     Heath
    0.87
    combe
    0.83
    row
    0.83
    mares
    0.83
    aday
    0.78
     Slater
    0.78
    gow
    0.76
    line
    0.75
    Activations Density 0.009%

    No Known Activations