© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 15267
    Prev
    Next
    INDEX
    Explanations

    news articles from Reuters

    oai_token-act-pair · gpt-3.5-turbo

    references to the news agency Reuters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ound
    -0.71
     grade
    -0.68
    ople
    -0.67
     Earl
    -0.64
     great
    -0.64
     darn
    -0.63
     Raven
    -0.62
     cam
    -0.62
     Gram
    -0.61
     damn
    -0.61
    POSITIVE LOGITS
    Reuters
    3.66
    AFP
    2.08
    Bloomberg
    2.00
     Reuters
    2.00
    EPA
    1.71
    UTERS
    1.64
     REUTERS
    1.62
    CNN
    1.61
    Getty
    1.55
    AP
    1.45
    Activations Density 0.006%

    No Known Activations