© 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. 7-RES-JB
    11. 22920
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic impact and trade agreements

    oai_token-act-pair · gpt-3.5-turbo

    references to economic impact and global trade dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.61
     ceremon
    -0.51
    BuyableInstoreAndOnline
    -0.51
    Newsletter
    -0.50
     Haunted
    -0.49
     brisk
    -0.48
     greeted
    -0.48
    efer
    -0.48
     Cheong
    -0.48
     largeDownload
    -0.47
    POSITIVE LOGITS
     alike
    0.74
     purposes
    0.71
     needy
    0.64
    ignty
    0.63
     industries
    0.62
    cially
    0.61
    arians
    0.61
     populations
    0.60
     taxp
    0.59
     constituents
    0.59
    Activations Density 0.946%

    No Known Activations