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. 8-RES-JB
    6. 12748
    Prev
    Next
    INDEX
    Explanations

    references to various sports and recreational activities

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of games and sports

    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
    ailability
    -0.79
     contingency
    -0.77
     departure
    -0.72
    catentry
    -0.69
     sugg
    -0.69
     departures
    -0.68
     semif
    -0.66
     dismissal
    -0.66
     tentative
    -0.66
     pestic
    -0.64
    POSITIVE LOGITS
     responsibly
    1.02
     aloud
    0.90
     abroad
    0.89
     wisely
    0.88
     efficiently
    0.86
     outdoors
    0.86
     faithfully
    0.86
     anonymously
    0.83
     onstage
    0.82
     differently
    0.82
    Activations Density 0.360%

    No Known Activations