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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16295
    Prev
    Next
    INDEX
    Explanations

    highlights related to specific locations, specifically focusing on "Smithsonian" and "Yellowstone."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific institutions and geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cao
    -0.81
    20439
    -0.76
    rael
    -0.72
     Aval
    -0.71
    gap
    -0.70
    oner
    -0.70
    osuke
    -0.69
    onz
    -0.68
    ramid
    -0.68
    eping
    -0.65
    POSITIVE LOGITS
     Institution
    1.36
    sonian
    1.17
     Smithsonian
    0.96
     museums
    0.93
    arium
    0.90
     Tropical
    0.90
     Expedition
    0.88
     Museum
    0.85
     honors
    0.81
    ĸļ
    0.81
    Activations Density 0.792%

    No Known Activations