© 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. 13850
    Prev
    Next
    INDEX
    Explanations

    words related to newspapers and journalism

    oai_token-act-pair · gpt-3.5-turbo

    references to various news publications and their reporting

    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
    wikipedia
    -0.71
     accommodation
    -0.70
    otin
    -0.70
    tumblr
    -0.69
    CVE
    -0.69
    wik
    -0.65
    chwitz
    -0.65
    milo
    -0.64
     goodwill
    -0.64
    etsy
    -0.63
    POSITIVE LOGITS
     Gazette
    1.25
     Tribune
    1.21
     Herald
    1.08
     Courier
    0.97
     Dispatch
    0.95
     Observer
    0.94
     Bulletin
    0.94
     Chronicle
    0.94
     Telegram
    0.92
     Sentinel
    0.92
    Activations Density 0.094%

    No Known Activations