© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 26518
    Prev
    Next
    INDEX
    Explanations

    medical conditions and diseases, particularly those related to cancer and chronic illnesses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.12
    2:0.02
    3:0.03
    4:0.02
    5:0.35
    6:0.03
    7:0.02
    8:0.04
    9:0.07
    10:0.13
    11:0.07
    Negative Logits
     Airl
    -1.87
     delegated
    -1.72
    Lago
    -1.68
     booth
    -1.67
    company
    -1.49
     furthe
    -1.48
     deft
    -1.47
     encour
    -1.45
     vot
    -1.44
    elvet
    -1.43
    POSITIVE LOGITS
     disease
    2.48
     diseases
    2.29
     Symptoms
    2.19
    icter
    2.19
     symptoms
    2.17
     psychosis
    2.16
     epile
    2.16
    emic
    2.15
     Syndrome
    2.14
    ptoms
    2.14
    Activations Density 0.082%

    No Known Activations