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. 21523
    Prev
    Next
    INDEX
    Explanations

    references to the physical organ of the eye

    oai_token-act-pair · gpt-3.5-turbo

    references to "Eye" across various contexts

    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
     delinqu
    -0.83
    merce
    -0.74
     segregation
    -0.69
    eting
    -0.69
     perm
    -0.68
     compromise
    -0.65
     propag
    -0.65
     basket
    -0.65
    rawdownloadcloneembedreportprint
    -0.64
     mang
    -0.64
    POSITIVE LOGITS
     Eye
    4.00
    Eye
    2.89
     Eyes
    2.05
    eye
    2.02
     eye
    1.64
     Ey
    1.48
    Ey
    1.41
     Mouth
    1.38
    eyes
    1.35
     Face
    1.17
    Activations Density 0.011%

    No Known Activations