© 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. 2-RES-JB
    11. 11826
    Prev
    Next
    INDEX
    Explanations

    news-related terms or headlines

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Breaking" as a signal of breaking news content

    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
    ogical
    -0.71
    lain
    -0.71
    GY
    -0.68
    trak
    -0.68
    oping
    -0.67
    inating
    -0.66
    ulp
    -0.64
    until
    -0.64
    haps
    -0.64
    minist
    -0.64
    POSITIVE LOGITS
     Breaking
    1.01
    breakers
    0.85
    Breaking
    0.85
    fast
    0.85
    AKING
    0.82
     Breaker
    0.80
    breaking
    0.77
     Bridges
    0.74
    Berry
    0.74
     Bad
    0.73
    Activations Density 0.005%

    No Known Activations