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. 5993
    Prev
    Next
    INDEX
    Explanations

    numerical values related to the quantity of one million

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "million."

    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
    anooga
    -0.78
    displayText
    -0.77
    swick
    -0.75
    anwhile
    -0.72
    icipated
    -0.70
    krit
    -0.67
    ivalry
    -0.67
    ivism
    -0.65
    ivity
    -0.65
    ibrary
    -0.65
    POSITIVE LOGITS
    aire
    1.03
    aires
    0.99
     dollars
    0.86
     dollar
    0.80
    dollar
    0.79
    ãĥĩãĤ£
    0.75
     hectares
    0.73
     Oaks
    0.73
     watts
    0.72
     miles
    0.72
    Activations Density 0.045%

    No Known Activations