© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 12219
    Prev
    Next
    INDEX
    Explanations

    specific medical conditions related to vision and eye health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.20
    1:0.02
    2:0.28
    3:0.09
    4:0.03
    5:0.12
    6:0.04
    7:0.04
    8:0.03
    9:0.06
    10:0.04
    11:0.02
    Negative Logits
    econom
    -2.77
    commit
    -2.61
     dumps
    -2.51
     Reign
    -2.35
    Econom
    -2.35
    20439
    -2.35
    git
    -2.35
    icides
    -2.33
     dumped
    -2.31
    aiden
    -2.31
    POSITIVE LOGITS
     retina
    4.70
     blindness
    4.46
     optic
    4.41
    ocular
    4.06
     blurry
    4.02
     optical
    3.83
     lenses
    3.82
     vision
    3.74
     magnification
    3.73
     glasses
    3.71
    Activations Density 0.069%

    No Known Activations