© 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. 10-RES-JB
    11. 11467
    Prev
    Next
    INDEX
    Explanations

    descriptions related to vision impairment and physical conditions of the eyes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to vision impairment and its causes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Heist
    -0.94
     Rebell
    -0.88
     Slaughter
    -0.87
     Nug
    -0.81
    conom
    -0.79
    é¾
    -0.78
     Beef
    -0.77
     Pork
    -0.77
     Weekend
    -0.76
    commit
    -0.75
    POSITIVE LOGITS
     retina
    1.62
     blindness
    1.61
     infrared
    1.41
     glare
    1.40
     blind
    1.39
    ocular
    1.38
     goggles
    1.38
     telescopes
    1.35
     optical
    1.35
     ultraviolet
    1.34
    Activations Density 0.509%

    No Known Activations