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

    Neuronpedia

    APICircuit 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. 19686
    Prev
    Next
    INDEX
    Explanations

    information related to economic or financial reports and studies

    oai_token-act-pair · gpt-3.5-turbo

    references to authoritative reports or studies, particularly those denoted by the phrase "according to."

    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
     rever
    -0.77
     preceded
    -0.75
    brainer
    -0.74
    selection
    -0.72
     sucks
    -0.71
     ensued
    -0.71
     engulf
    -0.70
     solves
    -0.69
     decides
    -0.66
    rats
    -0.66
    POSITIVE LOGITS
     Institute
    1.35
     Association
    1.35
     National
    1.25
     Center
    1.24
     Partnership
    1.18
     nonpartisan
    1.16
     nonprofit
    1.15
     Society
    1.15
     Centers
    1.14
     International
    1.13
    Activations Density 0.198%

    No Known Activations