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. 19496
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "play" in the context of sports or performance

    oai_token-act-pair · gpt-3.5-turbo

    references to specific plays in sports contexts

    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
    «ĺ
    -0.76
     Apost
    -0.69
     unden
    -0.67
     Beir
    -0.65
     Unic
    -0.64
    ++++++++++++++++
    -0.64
     exclusive
    -0.63
    pora
    -0.62
    orpor
    -0.62
     captivity
    -0.62
    POSITIVE LOGITS
    ername
    1.35
    wright
    1.27
    maker
    1.22
    plays
    1.08
    makers
    1.06
    styles
    0.99
    making
    0.99
    wr
    0.99
    tes
    0.98
    testers
    0.96
    Activations Density 0.041%

    No Known Activations