© 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. 11-RES-JB
    11. 1009
    Prev
    Next
    INDEX
    Explanations

    mentions of famous landmarks and historical sites

    oai_token-act-pair · gpt-3.5-turbo

    prominent landmarks and significant architectural sites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Parent
    -0.84
    Recommend
    -0.82
    ebook
    -0.79
    ername
    -0.78
    Label
    -0.77
    IU
    -0.74
    Issue
    -0.72
    Cole
    -0.72
    Account
    -0.72
    epad
    -0.72
    POSITIVE LOGITS
     Statue
    1.44
     Titanic
    1.37
     volcano
    1.25
     skysc
    1.23
     skyline
    1.22
    ramids
    1.21
     castles
    1.20
     fireworks
    1.20
     Disneyland
    1.19
     sculptures
    1.17
    Activations Density 0.559%

    No Known Activations