© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 8460
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, specifically focusing on the state of Florida

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of Florida

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cliffe
    -0.78
    åĤ
    -0.78
    LOAD
    -0.77
    hide
    -0.74
    selves
    -0.74
    roma
    -0.74
    chel
    -0.72
    bour
    -0.71
    çĦ
    -0.71
    haar
    -0.68
    POSITIVE LOGITS
     Gators
    1.16
     Panthers
    1.00
    herty
    0.91
     Keys
    0.91
     Atlantic
    0.90
     Marlins
    0.86
     State
    0.85
     Springs
    0.85
    sylvania
    0.82
    avorable
    0.79
    Activations Density 0.018%

    No Known Activations