© 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. 11-RES-JB
    11. 20797
    Prev
    Next
    INDEX
    Explanations

    news organization names, specifically "Reuters"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of 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 @ 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
    chest
    -0.88
    rette
    -0.76
    inent
    -0.76
    rous
    -0.73
    pired
    -0.72
    lain
    -0.71
    plate
    -0.67
    ãĥ¼ãĤ¯
    -0.66
     wedge
    -0.65
    jury
    -0.65
    POSITIVE LOGITS
     Newsp
    0.82
    Money
    0.80
     correspondent
    0.77
     Helic
    0.75
    Asia
    0.74
     Health
    0.73
     Markets
    0.72
     Features
    0.71
     News
    0.71
     Television
    0.71
    Activations Density 0.025%

    No Known Activations