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. 10-RES-JB
    6. 19440
    Prev
    Next
    INDEX
    Explanations

    percentages, trends, and numeric data related to various changes or events

    oai_token-act-pair · gpt-3.5-turbo

    numeric data related to crime statistics and changes in rates

    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
     vetted
    -0.68
     entrusted
    -0.67
     imagin
    -0.66
     wisely
    -0.66
     tasked
    -0.64
     Laboratories
    -0.64
     smelled
    -0.63
     meticulously
    -0.63
     spies
    -0.63
     Tycoon
    -0.63
    POSITIVE LOGITS
     increase
    1.80
     decrease
    1.79
     uptick
    1.73
     decline
    1.66
     improvement
    1.60
     declines
    1.59
     increases
    1.59
     decreases
    1.55
     slowdown
    1.49
     rise
    1.46
    Activations Density 0.413%

    No Known Activations