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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2498
    Prev
    Next
    INDEX
    Explanations

    words related to astronomy and astrological concepts, especially those related to "Astro"

    oai_token-act-pair · gpt-3.5-turbo

    references to "astro" or space-related terms in the context of research and funding

    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
     CTR
    -0.71
     SCP
    -0.69
     subp
    -0.67
     balloons
    -0.65
    */(
    -0.63
     inconsist
    -0.62
    ãĥ£
    -0.60
     marble
    -0.59
     litter
    -0.58
     act
    -0.58
    POSITIVE LOGITS
    Zen
    0.95
     Pradesh
    0.81
    lake
    0.78
    abe
    0.78
     Abbey
    0.77
    iland
    0.76
    INA
    0.75
    alia
    0.73
    ogical
    0.72
    intestinal
    0.71
    Activations Density 0.135%

    No Known Activations