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. 16303
    Prev
    Next
    INDEX
    Explanations

    words related to a specific term "Cy" or "Cyprus"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific award named after a notable individual

    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
     grill
    -0.77
     badge
    -0.76
    agher
    -0.74
     reservation
    -0.71
    ãģ¦
    -0.69
    eele
    -0.68
    Graham
    -0.68
    assed
    -0.67
    oor
    -0.67
    ormal
    -0.66
    POSITIVE LOGITS
     Cy
    4.01
    Cy
    2.62
     Cycl
    1.92
     cy
    1.86
     CY
    1.85
    cy
    1.77
     Cyprus
    1.67
     cycl
    1.60
     Cyp
    1.45
     Cycle
    1.27
    Activations Density 0.021%

    No Known Activations