Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2381
    Prev
    Next
    INDEX
    Explanations

    dates written in a specific format (month day, year) accompanied by an author's name or title

    oai_token-act-pair · gpt-3.5-turbo

    instances of dates and their formatting in texts

    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
     tram
    -0.76
     appoint
    -0.76
     confir
    -0.76
     sculpt
    -0.75
     tack
    -0.70
     funnel
    -0.70
     eleph
    -0.69
     estab
    -0.69
     scrap
    -0.68
     elect
    -0.68
    POSITIVE LOGITS
    Introduction
    1.89
    Enlarge
    1.69
    Overview
    1.58
    Posted
    1.56
    Welcome
    1.55
    toggle
    1.54
    Dear
    1.54
    Hello
    1.50
    Guest
    1.49
    Published
    1.49
    Activations Density 0.286%

    No Known Activations