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. 8-RES-JB
    6. 18889
    Prev
    Next
    INDEX
    Explanations

    phrases related to projects, developments, and plans

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the development or introduction of new products, technologies, or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IMAGES
    -0.72
     Gleaming
    -0.70
     Pers
    -0.69
     Units
    -0.68
     Numbers
    -0.66
     Occupations
    -0.65
    inventoryQuantity
    -0.65
     Levels
    -0.64
     newsletters
    -0.64
     Convers
    -0.63
    POSITIVE LOGITS
     underway
    0.95
    ritten
    0.89
     ensued
    0.85
    ugi
    0.80
     imminent
    0.77
    agraph
    0.76
    acci
    0.73
    wana
    0.72
    itialized
    0.72
    emaker
    0.72
    Activations Density 0.464%

    No Known Activations