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. 15612
    Prev
    Next
    INDEX
    Explanations

    words related to rockets or rocket-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to rockets and rocket-related technology

    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
    redo
    -0.87
     Borders
    -0.79
    DonaldTrump
    -0.77
    tale
    -0.72
    oral
    -0.66
    ktop
    -0.64
    ures
    -0.62
    ORD
    -0.62
    arettes
    -0.62
    say
    -0.61
    POSITIVE LOGITS
    eers
    1.03
     launcher
    1.01
    ulic
    0.99
    laun
    0.98
     propelled
    0.96
     launchers
    0.95
    eer
    0.93
     propulsion
    0.89
     Launcher
    0.88
     propell
    0.84
    Activations Density 0.028%

    No Known Activations