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. 5-RES-JB
    6. 19469
    Prev
    Next
    INDEX
    Explanations

    words related to space exploration and astronomy, particularly the Hubble Space Telescope and Kepler missions

    oai_token-act-pair · gpt-3.5-turbo

    references to telescopes, particularly the Hubble and Kepler telescopes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onym
    -0.80
    stood
    -0.79
    ramid
    -0.73
    iquid
    -0.69
    ammy
    -0.69
    ulhu
    -0.68
    lopp
    -0.68
    onies
    -0.67
    pron
    -0.67
    eanor
    -0.67
    POSITIVE LOGITS
     Hubble
    0.96
     Telescope
    0.90
     telescope
    0.81
     Goddard
    0.80
     Observatory
    0.77
    Eye
    0.73
     Images
    0.73
     Imaging
    0.72
     rays
    0.71
     zo
    0.71
    Activations Density 0.014%

    No Known Activations