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. 10-RES-JB
    6. 257
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic institutions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of institutions or entities associated with "the."

    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
    bledon
    -0.71
    wagen
    -0.67
    lock
    -0.62
    fare
    -0.61
    jay
    -0.60
    */(
    -0.60
    oliath
    -0.59
     competitors
    -0.59
     jour
    -0.58
     sorcery
    -0.58
    POSITIVE LOGITS
     Philippines
    0.94
     Causes
    0.87
     Ancients
    0.84
     United
    0.84
     Hague
    0.84
     Netherlands
    0.82
     Blind
    0.80
     Arts
    0.80
     Republic
    0.80
     Americas
    0.80
    Activations Density 0.068%

    No Known Activations