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. 0-RES-JB
    6. 17664
    Prev
    Next
    INDEX
    Explanations

    references to cruise-related activities or objects

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "cruise" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hw
    -0.76
    ById
    -0.73
     Almighty
    -0.70
     Texture
    -0.69
    00000
    -0.65
    Ł
    -0.65
     Ars
    -0.63
    ells
    -0.63
     Micha
    -0.63
    holder
    -0.62
    POSITIVE LOGITS
     cruise
    4.11
     Cruise
    3.00
     cruising
    2.02
     sail
    1.47
    Cru
    1.44
    cru
    1.44
     voyage
    1.34
     sailing
    1.34
     cru
    1.28
     paddle
    1.19
    Activations Density 0.009%

    No Known Activations