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. 19643
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to astronomy and physics

    oai_token-act-pair · gpt-3.5-turbo

    elements relating to astrophysics and cosmic phenomena

    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
    iquette
    -0.90
    ilet
    -0.82
     Homeless
    -0.78
    oshop
    -0.74
     Franch
    -0.71
     toile
    -0.70
    Atlanta
    -0.70
     ADA
    -0.69
    street
    -0.69
    ****************
    -0.68
    POSITIVE LOGITS
     electrons
    1.10
     neutron
    1.05
     astronomers
    1.02
     interstellar
    1.00
     Uran
    0.94
     physicists
    0.90
     extrater
    0.89
     graphene
    0.89
     cosmic
    0.88
     radiation
    0.88
    Activations Density 0.512%

    No Known Activations