© 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. 22321
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to breaking news announcements

    oai_token-act-pair · gpt-3.5-turbo

    mentions of breaking news

    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
    Reviewer
    -0.77
     Ratio
    -0.70
    ħĭ
    -0.70
     Grimoire
    -0.66
    terness
    -0.65
     Catal
    -0.63
    Registered
    -0.62
     Slave
    -0.61
     Handling
    -0.61
     tremend
    -0.59
    POSITIVE LOGITS
     news
    0.98
     NEWS
    0.79
    news
    0.74
     info
    0.68
     intel
    0.66
    BUS
    0.65
     information
    0.65
    Trend
    0.64
    NEWS
    0.62
     emergencies
    0.61
    Activations Density 0.012%

    No Known Activations