© 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. 4-RES-JB
    11. 7190
    Prev
    Next
    INDEX
    Explanations

    mentions of trade-related partnerships or agreements, specifically those involving the word "Trans"

    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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sunder
    -0.73
    vre
    -0.72
     WARN
    -0.71
    RANT
    -0.70
    âķIJâķIJ
    -0.70
     4090
    -0.69
     WARRANT
    -0.65
    ELL
    -0.65
     jo
    -0.64
    mble
    -0.64
    POSITIVE LOGITS
    gender
    1.00
    cend
    0.98
    lator
    0.98
    sexual
    0.89
    lucent
    0.88
    missions
    0.88
    gress
    0.87
    ference
    0.87
    dimensional
    0.86
    porter
    0.86
    Activations Density 0.010%

    No Known Activations