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. 2900
    Prev
    Next
    INDEX
    Explanations

    number-related strings

    oai_token-act-pair · gpt-3.5-turbo

    data related to percentages and statistical values

    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
    pedia
    -0.64
    pecially
    -0.63
     cul
    -0.58
    EStream
    -0.58
    ometime
    -0.58
     itiner
    -0.58
    etheus
    -0.57
     inconsist
    -0.57
    cules
    -0.57
    jamin
    -0.57
    POSITIVE LOGITS
    lycer
    0.86
     GDP
    0.82
     rate
    0.80
     Rate
    0.75
    elsen
    0.73
     variance
    0.72
    ococ
    0.71
    elsius
    0.71
    ved
    0.71
     (%
    0.70
    Activations Density 0.233%

    No Known Activations