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. 9-RES-JB
    6. 10876
    Prev
    Next
    INDEX
    Explanations

    references to national anthems

    oai_token-act-pair · gpt-3.5-turbo

    references to the national anthem and related social issues or protests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sor
    -0.76
    Medium
    -0.69
     Dynamics
    -0.67
    neau
    -0.66
     Thumbnails
    -0.66
    angs
    -0.65
    aido
    -0.65
    erm
    -0.63
     Manor
    -0.62
    Magazine
    -0.62
    POSITIVE LOGITS
    aepernick
    1.10
     anthem
    1.01
     kneeling
    0.92
     Kaepernick
    0.90
     salute
    0.83
     kne
    0.82
     protests
    0.79
     Anthem
    0.78
    brance
    0.76
     honoring
    0.76
    Activations Density 0.080%

    No Known Activations