© 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. 10107
    Prev
    Next
    INDEX
    Explanations

    mentions of the Canadian Broadcasting Corporation (CBC)

    oai_token-act-pair · gpt-3.5-turbo

    references to Canadian news and media outlets

    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
    apache
    -0.91
    andowski
    -0.91
    amsung
    -0.88
    Äĩ
    -0.83
     Ultron
    -0.82
    Reviewer
    -0.80
     java
    -0.76
    lio
    -0.76
    java
    -0.74
     mysql
    -0.74
    POSITIVE LOGITS
     Canadians
    2.10
     Ottawa
    2.10
     Manitoba
    2.04
     Alberta
    2.04
     Saskatchewan
    2.04
     RCMP
    2.03
     Canada
    2.01
     NDP
    1.99
     Trudeau
    1.98
    Canada
    1.97
    Activations Density 1.233%

    No Known Activations