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. 20212
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographical locations, especially in Florida

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Florida and its related locations or entities

    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
     Redemption
    -0.77
    selves
    -0.67
     bulls
    -0.67
    ELL
    -0.65
     buckle
    -0.65
     brace
    -0.63
    arters
    -0.63
    PC
    -0.62
     Shack
    -0.62
     mate
    -0.62
    POSITIVE LOGITS
    mingham
    0.95
    idian
    0.92
    hess
    0.91
    idan
    0.88
    issance
    0.86
    iculture
    0.86
    iane
    0.85
    oso
    0.83
    ifer
    0.81
    ately
    0.80
    Activations Density 0.029%

    No Known Activations