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. 21944
    Prev
    Next
    INDEX
    Explanations

    mentions of boats

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "boat" in various contexts

    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
    arial
    -0.78
    uate
    -0.67
    heimer
    -0.67
    ipher
    -0.64
    orian
    -0.64
     Lamar
    -0.63
     Horowitz
    -0.63
    ENCE
    -0.63
     Staples
    -0.63
    Interstitial
    -0.62
    POSITIVE LOGITS
    boat
    1.19
    wright
    1.16
    loads
    1.13
    boats
    1.08
     sailing
    1.00
     Graveyard
    0.99
     boats
    0.99
    load
    0.98
     boat
    0.97
     sailed
    0.97
    Activations Density 0.030%

    No Known Activations