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. 7-RES-JB
    6. 14932
    Prev
    Next
    INDEX
    Explanations

    phrases related to galaxies and astronomical observations

    oai_token-act-pair · gpt-3.5-turbo

    references to galaxies and related astronomical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ership
    -0.77
    thodox
    -0.75
    ieth
    -0.75
    iaz
    -0.72
    pee
    -0.71
    ichita
    -0.71
    udo
    -0.71
    IED
    -0.71
    essee
    -0.71
    ointed
    -0.71
    POSITIVE LOGITS
    arium
    0.94
     rays
    0.90
     galaxy
    0.87
     Milky
    0.84
     galaxies
    0.78
     violet
    0.76
     Telescope
    0.76
     cosmic
    0.76
     Andromeda
    0.75
     Nebula
    0.74
    Activations Density 0.021%

    No Known Activations