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. 18172
    Prev
    Next
    INDEX
    Explanations

    numbers and financial terms such as prices, locations, and quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and references related to financial or geographical statistics

    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
    etsy
    -0.70
     Sochi
    -0.62
     Adin
    -0.61
     laz
    -0.59
     crate
    -0.59
     Satanic
    -0.58
    ffee
    -0.55
     recess
    -0.55
     Antar
    -0.55
     Bulgar
    -0.55
    POSITIVE LOGITS
    byss
    0.80
    OTAL
    0.76
    Quantity
    0.74
     ..............
    0.73
    iovascular
    0.71
    MSN
    0.70
    ommod
    0.69
    antam
    0.65
    Us
    0.64
    endish
    0.63
    Activations Density 0.241%

    No Known Activations