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. 11-RES-JB
    6. 10427
    Prev
    Next
    INDEX
    Explanations

    specific terms related to telescopes and observatories

    oai_token-act-pair · gpt-3.5-turbo

    references to astronomical observations and technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thug
    -0.85
    agin
    -0.82
    izophren
    -0.80
    ifest
    -0.78
    hemy
    -0.74
    ombies
    -0.73
     Rape
    -0.73
     undone
    -0.72
     mattress
    -0.72
    ilege
    -0.71
    POSITIVE LOGITS
     telescopes
    1.85
     satellites
    1.76
     telescope
    1.69
     Galileo
    1.55
     astronomers
    1.51
     Hubble
    1.50
     spacecraft
    1.49
     satellite
    1.45
     Telesc
    1.45
     Telescope
    1.42
    Activations Density 0.313%

    No Known Activations