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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 20106
    Prev
    Next
    INDEX
    Explanations

    phrases related to international collaboration and activities involving different countries

    oai_token-act-pair · gpt-3.5-turbo

    prepositions, specifically the word "for" and similar phrases indicating purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Owner
    -0.66
    Strange
    -0.65
    Fle
    -0.65
    MJ
    -0.64
    mare
    -0.64
    LAB
    -0.63
    edin
    -0.63
    fleet
    -0.63
    KK
    -0.61
    plate
    -0.60
    POSITIVE LOGITS
    geries
    1.17
     example
    1.03
    bidden
    1.03
    ked
    1.01
     instance
    1.00
     purposes
    0.98
    gery
    0.94
    gotten
    0.93
     centuries
    0.89
    cible
    0.87
    Activations Density 0.308%

    No Known Activations