© 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. 4-RES-JB
    6. 15893
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "Oregon."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the state of Oregon

    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
    hare
    -0.94
    BOOK
    -0.86
    maid
    -0.81
    pter
    -0.74
    bler
    -0.70
    stroke
    -0.70
    SHIP
    -0.69
     seiz
    -0.69
    bour
    -0.69
    uds
    -0.68
    POSITIVE LOGITS
     Oregon
    1.03
    sylvania
    0.92
     State
    0.91
     Ducks
    0.89
    Oregon
    0.88
    icut
    0.86
     Hills
    0.85
    ians
    0.84
     Timbers
    0.84
    ian
    0.80
    Activations Density 0.008%

    No Known Activations