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. 4-RES-JB
    6. 3161
    Prev
    Next
    INDEX
    Explanations

    references to international agreements and conventions

    oai_token-act-pair · gpt-3.5-turbo

    references to international conventions and agreements related to climate change

    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
    rosse
    -0.85
    esville
    -0.79
     Lansing
    -0.76
    waukee
    -0.73
    juries
    -0.72
    icago
    -0.70
    nesota
    -0.69
    espie
    -0.69
    ItemImage
    -0.69
    eah
    -0.67
    POSITIVE LOGITS
     Implementation
    0.99
     treaty
    0.99
     Framework
    0.96
     ratified
    0.95
     treaties
    0.94
     Treaty
    0.93
     Agreement
    0.91
     UNESCO
    0.90
     Programme
    0.87
    ilateral
    0.85
    Activations Density 0.188%

    No Known Activations