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. 8-RES-JB
    6. 21895
    Prev
    Next
    INDEX
    Explanations

    terms related to climate science and studies

    oai_token-act-pair · gpt-3.5-turbo

    scientific and technical terminology related to climate and atmospheric studies

    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
     Cheong
    -0.76
     Jub
    -0.69
     Hallow
    -0.68
     Kiw
    -0.67
     Cay
    -0.63
     Cros
    -0.63
     Garrison
    -0.62
     Cullen
    -0.62
    church
    -0.61
     Wellington
    -0.61
    POSITIVE LOGITS
    ically
    1.28
    icians
    1.07
    ochemical
    1.03
    ologists
    1.02
    ological
    1.00
    ician
    0.99
    ics
    0.99
    ische
    0.98
    alyst
    0.98
    ICAL
    0.97
    Activations Density 0.126%

    No Known Activations