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. 0-RES-JB
    6. 5971
    Prev
    Next
    INDEX
    Explanations

    phrases related to astronomy and space

    oai_token-act-pair · gpt-3.5-turbo

    references to astronomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PK
    -0.80
     trough
    -0.76
    NetMessage
    -0.74
     fault
    -0.69
     lim
    -0.68
     responsive
    -0.68
     quarrel
    -0.67
    eed
    -0.67
     mills
    -0.67
     resent
    -0.67
    POSITIVE LOGITS
     Astron
    3.87
    Ast
    2.05
     astronaut
    1.67
     astronomy
    1.42
     Philos
    1.34
     Meteor
    1.31
     Astro
    1.29
     Ancient
    1.26
     astroph
    1.25
     Geological
    1.25
    Activations Density 0.024%

    No Known Activations