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. 1-RES-JB
    6. 1409
    Prev
    Next
    INDEX
    Explanations

    specific mentions of a katana sword

    oai_token-act-pair · gpt-3.5-turbo

    references to specific types of weapons, particularly katanas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antha
    -0.69
    tymology
    -0.67
     ItemLevel
    -0.62
     Grind
    -0.62
    agall
    -0.62
     Settings
    -0.62
     Tid
    -0.62
     Petraeus
    -0.61
    aments
    -0.60
    stals
    -0.60
    POSITIVE LOGITS
    erie
    0.86
    ablish
    0.78
    conservancy
    0.75
    cedented
    0.70
    aughs
    0.69
     brake
    0.65
    ablished
    0.63
    accompan
    0.62
    rez
    0.61
    htaking
    0.60
    Activations Density 0.000%

    No Known Activations