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. 20735
    Prev
    Next
    INDEX
    Explanations

    references to naval vessels

    oai_token-act-pair · gpt-3.5-turbo

    mentions of naval vessels, specifically aircraft carriers and their identification numbers

    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
    izophren
    -0.81
    okin
    -0.78
    aum
    -0.72
    otropic
    -0.70
    rency
    -0.70
    xus
    -0.69
     ingred
    -0.67
    ultane
    -0.67
    âķIJâķIJ
    -0.67
    ject
    -0.67
    POSITIVE LOGITS
     USS
    1.20
     Yamato
    0.99
     Voyager
    0.99
     HMS
    0.97
     Titanic
    0.96
     Enterprise
    0.93
     cruiser
    0.88
     fleet
    0.84
     Admiral
    0.84
    USS
    0.84
    Activations Density 0.073%

    No Known Activations