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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 5972
    Prev
    Next
    INDEX
    Explanations

    references to international agreements or treaties

    oai_token-act-pair · gpt-3.5-turbo

    references to international agreements and aviation regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abilia
    -0.94
     stash
    -0.91
     pickup
    -0.89
     pricey
    -0.87
     Glow
    -0.86
     dime
    -0.85
     booze
    -0.84
     Craigslist
    -0.83
     kids
    -0.81
     garage
    -0.78
    POSITIVE LOGITS
     ratified
    1.33
     ratification
    1.26
     UNESCO
    1.16
     unanimously
    1.12
     recognised
    1.10
     treaties
    1.09
     bilateral
    1.04
     Article
    1.03
     Parties
    1.02
     Parliamentary
    1.02
    Activations Density 1.058%

    No Known Activations