© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 2145
    Prev
    Next
    INDEX
    Explanations

    references related to the state of Florida or specific Floridian cities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Florida and related entities

    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
     Redemption
    -0.82
     buckle
    -0.75
    selves
    -0.69
    PC
    -0.68
    CHR
    -0.67
     thumbs
    -0.66
     bulls
    -0.66
     stroke
    -0.63
    arter
    -0.63
     revolving
    -0.63
    POSITIVE LOGITS
    iane
    0.90
    idian
    0.88
    iculture
    0.87
    itor
    0.82
    asma
    0.82
    mingham
    0.81
    idan
    0.81
    ian
    0.81
    oso
    0.81
    ifer
    0.80
    Activations Density 0.006%

    No Known Activations