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. 8599
    Prev
    Next
    INDEX
    Explanations

    references to the Apollo missions, particularly Apollo 9 and 10

    oai_token-act-pair · gpt-3.5-turbo

    references to the Apollo 9 mission

    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
    lev
    -0.75
    ª
    -0.69
     latt
    -0.68
     --------
    -0.68
     towns
    -0.68
    Hung
    -0.67
    iter
    -0.66
     hasht
    -0.64
     weaken
    -0.64
     weak
    -0.62
    POSITIVE LOGITS
     Apollo
    4.07
     Artemis
    1.60
     Gemini
    1.60
     Mercury
    1.60
     Ares
    1.52
     Hermes
    1.45
    ollo
    1.44
     Juno
    1.42
     Prometheus
    1.41
     Osiris
    1.38
    Activations Density 0.018%

    No Known Activations