© 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. 7805
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical locations or destinations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to physical locations and significant entities

    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
    20439
    -0.79
    rep
    -0.79
    Intel
    -0.76
    accompan
    -0.76
    ANI
    -0.75
    pract
    -0.75
    Josh
    -0.73
    Ja
    -0.72
     acron
    -0.71
    jin
    -0.71
    POSITIVE LOGITS
     area
    1.02
     dome
    1.01
     space
    1.00
     zone
    0.99
     premises
    0.99
     Palace
    0.99
     atmosphere
    0.98
     avenue
    0.96
     palace
    0.95
     location
    0.95
    Activations Density 0.507%

    No Known Activations