© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 4541
    Prev
    Next
    INDEX
    Explanations

    phrases related to celestial bodies and astronomical observations

    oai_token-act-pair · gpt-3.5-turbo

    references to celestial bodies and astronomical phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    street
    -0.93
    iquette
    -0.84
     Criminal
    -0.84
     appl
    -0.82
    skill
    -0.82
    olicy
    -0.80
     Lawyers
    -0.79
    Accessory
    -0.78
    Prosecut
    -0.78
    Compl
    -0.77
    POSITIVE LOGITS
     orbiting
    1.51
     orbits
    1.36
     asteroids
    1.33
     asteroid
    1.30
     Earth
    1.30
     planet
    1.27
     habitable
    1.25
     geological
    1.24
     Uran
    1.22
     astronomers
    1.22
    Activations Density 0.966%

    No Known Activations