© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 17236
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "a million"

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities or amounts, particularly involving the term "million."

    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
    ibaba
    -0.78
    graded
    -0.72
    raints
    -0.71
    anooga
    -0.70
    ivity
    -0.68
    grades
    -0.68
    ensions
    -0.67
    atility
    -0.65
    ivalry
    -0.63
    ibrary
    -0.63
    POSITIVE LOGITS
     dollars
    0.87
    aire
    0.83
     dollar
    0.82
    aires
    0.80
    ãĥĩãĤ£
    0.74
    dollar
    0.73
     fold
    0.72
    agy
    0.72
     bucks
    0.70
     watts
    0.69
    Activations Density 0.038%

    No Known Activations