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. 9-RES-JB
    6. 12802
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of "first-hand" experiences or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to firsthand experiences or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gould
    -0.73
     Canaver
    -0.69
     Tant
    -0.66
     Doomsday
    -0.62
    Downloadha
    -0.60
     Shutterstock
    -0.59
     Nadu
    -0.56
    Quantity
    -0.56
     Associ
    -0.55
     HERO
    -0.54
    POSITIVE LOGITS
     responders
    1.24
     baseman
    1.12
     ancest
    0.83
     impressions
    0.82
     glance
    0.81
     timers
    0.81
     impression
    0.80
    hand
    0.80
     blush
    0.79
     lady
    0.75
    Activations Density 0.081%

    No Known Activations