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. 3-RES-JB
    6. 1659
    Prev
    Next
    INDEX
    Explanations

    the term "Milky Way" or similar references to astronomy

    oai_token-act-pair · gpt-3.5-turbo

    references to the Milky Way galaxy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angers
    -0.76
    xual
    -0.73
    */(
    -0.73
    orney
    -0.72
    ovic
    -0.71
    PM
    -0.71
    uberty
    -0.70
    aughs
    -0.70
    ainer
    -0.70
    ued
    -0.70
    POSITIVE LOGITS
     Milky
    1.11
     Galaxy
    0.82
     Ways
    0.81
     Doodle
    0.80
     Telescope
    0.79
     galaxy
    0.76
    thora
    0.75
    ota
    0.75
     stripe
    0.74
     lapt
    0.73
    Activations Density 0.008%

    No Known Activations