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. 14432
    Prev
    Next
    INDEX
    Explanations

    large numerical values, specifically related to money, taxes, and statistics

    oai_token-act-pair · gpt-3.5-turbo

    financial figures and statistics

    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
    >:
    -0.56
    gewater
    -0.53
     Encyclopedia
    -0.53
    .):
    -0.53
    look
    -0.53
     Hancock
    -0.53
     -----
    -0.52
     Druid
    -0.50
    Overview
    -0.50
    Labor
    -0.50
    POSITIVE LOGITS
     thereafter
    1.17
     respectively
    0.83
     afterward
    0.82
     when
    0.76
     apiece
    0.75
     if
    0.74
     versa
    0.74
     for
    0.72
     afterwards
    0.71
     during
    0.70
    Activations Density 0.227%

    No Known Activations