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. 7-RES-JB
    6. 6772
    Prev
    Next
    INDEX
    Explanations

    specific locations, particularly related to the Hudson River

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographic locations or landmarks, particularly "Hudson."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISTER
    -0.79
    ion
    -0.71
    vol
    -0.70
    fully
    -0.70
    igned
    -0.69
    orius
    -0.68
    ignment
    -0.68
    cious
    -0.68
    wagen
    -0.68
    igning
    -0.67
    POSITIVE LOGITS
     Yards
    1.02
     Valley
    0.85
     Strait
    0.81
     Bay
    0.77
     Hudson
    0.77
    ously
    0.77
     Falls
    0.74
    dale
    0.73
     Basin
    0.71
    é¾įåĸļ士
    0.70
    Activations Density 0.032%

    No Known Activations