© 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 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. 6012
    Prev
    Next
    INDEX
    Explanations

    references to international trade agreements, specifically those containing the word "Trans" followed by numbers and/or symbols

    oai_token-act-pair · gpt-3.5-turbo

    references to the Trans-Pacific Partnership trade agreement

    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
    ously
    -0.83
     bent
    -0.71
     cracking
    -0.68
     correction
    -0.67
     inacc
    -0.65
     disse
    -0.64
    RANT
    -0.62
     bats
    -0.60
     apparatus
    -0.59
     weakness
    -0.59
    POSITIVE LOGITS
    cend
    1.29
    continental
    1.27
    atlantic
    1.25
    gress
    1.23
    lucent
    1.14
    itional
    1.12
    lator
    1.11
    ferred
    1.10
    ient
    1.08
    mitt
    1.08
    Activations Density 0.013%

    No Known Activations