© 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. 10-RES-JB
    11. 2237
    Prev
    Next
    INDEX
    Explanations

    mentions of the publication "USA Today."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the organization "USA Today."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ragon
    -0.77
    tons
    -0.75
    ezvous
    -0.75
    ership
    -0.73
    erey
    -0.69
    ebook
    -0.68
    lords
    -0.66
    urger
    -0.66
     targ
    -0.66
    acles
    -0.66
    POSITIVE LOGITS
     TODAY
    1.50
     Today
    1.17
    ID
    1.01
    BILITY
    0.93
    ICAN
    0.92
    ITE
    0.90
    ESSION
    0.88
    JO
    0.86
    BA
    0.86
    ADA
    0.85
    Activations Density 0.023%

    No Known Activations