Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 18885
    Prev
    Next
    INDEX
    Explanations

    information related to the moon and other celestial bodies, specifically focusing on the lunar surface and planetary interactions

    oai_token-act-pair · gpt-3.5-turbo

    references to celestial bodies, specifically lunar and planetary themes

    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
    chens
    -0.98
    lessly
    -0.95
    hered
    -0.92
    Downloadha
    -0.90
    edin
    -0.88
    llan
    -0.88
    urat
    -0.87
    tower
    -0.86
    enment
    -0.84
    wright
    -0.83
    POSITIVE LOGITS
    ities
    1.11
    ized
    1.03
    ised
    0.92
    ity
    0.91
     liberties
    0.91
    ization
    0.90
     significance
    0.88
    izing
    0.81
     origins
    0.81
     entities
    0.81
    Activations Density 0.132%

    No Known Activations