© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 6540
    Prev
    Next
    INDEX
    Explanations

    symptoms and conditions related to medical issues

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.08
    1:0.05
    2:0.06
    3:0.07
    4:0.14
    5:0.04
    6:0.07
    7:0.18
    8:0.02
    9:0.05
    10:0.06
    11:0.14
    Negative Logits
    ikuman
    -2.19
     Shir
    -2.19
    emetery
    -2.14
    jobs
    -2.12
    ahime
    -2.10
    ouver
    -2.08
    aciously
    -2.06
    ammy
    -2.04
    uyomi
    -2.04
    amus
    -2.04
    POSITIVE LOGITS
     symptoms
    3.29
     manifestations
    2.94
     signs
    2.91
     Signs
    2.87
     Symptoms
    2.78
    ptoms
    2.67
     sensations
    2.56
     symptom
    2.56
     hallucinations
    2.44
     visuals
    2.37
    Activations Density 0.004%

    No Known Activations