Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 8093
    Prev
    Next
    INDEX
    Explanations

    financial terms and company-related information

    oai_token-act-pair · gpt-3.5-turbo

    monetary values in transactions or financial contexts

    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
    apache
    -0.82
    Reviewer
    -0.79
    amsung
    -0.77
    andowski
    -0.77
    java
    -0.74
    lio
    -0.71
     ATL
    -0.71
    Äĩ
    -0.70
     Kore
    -0.69
     Nikola
    -0.69
    POSITIVE LOGITS
     Saskatchewan
    2.05
     Manitoba
    2.05
     Ottawa
    2.01
     Canadians
    1.98
     Alberta
    1.96
     RCMP
    1.96
     Winnipeg
    1.93
     NDP
    1.92
     Quebec
    1.90
     Ontario
    1.87
    Activations Density 2.238%

    No Known Activations