Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 10822
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific location, Tiananmen Square

    oai_token-act-pair · gpt-3.5-turbo

    references to Tiananmen Square and related political figures or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owitz
    -0.78
    itably
    -0.69
    crew
    -0.69
     theory
    -0.68
     reneg
    -0.62
     gem
    -0.62
     situ
    -0.61
     cartel
    -0.61
     missionary
    -0.61
    WARNING
    -0.60
    POSITIVE LOGITS
    iture
    0.84
     Horton
    0.76
    zza
    0.75
    auld
    0.75
    idav
    0.73
    gotten
    0.72
    erences
    0.72
    iling
    0.71
    cht
    0.69
    yre
    0.69
    Activations Density 0.023%

    No Known Activations