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. 6-RES-JB
    6. 16422
    Prev
    Next
    INDEX
    Explanations

    words related to various activities and professions, especially those involving sports and international relations

    oai_token-act-pair · gpt-3.5-turbo

    references to business and various types of sports events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nept
    -0.62
    stood
    -0.60
     Neighborhood
    -0.58
     slug
    -0.56
     Ninth
    -0.56
     Intellectual
    -0.54
     tidal
    -0.53
     GN
    -0.53
     MOR
    -0.53
     matchup
    -0.53
    POSITIVE LOGITS
     abroad
    0.88
     whilst
    0.81
     responsibly
    0.80
     while
    0.71
     cheaply
    0.71
     differently
    0.70
     Without
    0.70
    reply
    0.69
     without
    0.69
    java
    0.68
    Activations Density 0.335%

    No Known Activations