Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 2827
    Prev
    Next
    INDEX
    Explanations

    mentions of viruses and infectious diseases

    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
    0:0.03
    1:0.01
    2:0.06
    3:0.05
    4:0.04
    5:0.05
    6:0.22
    7:0.13
    8:0.03
    9:0.06
    10:0.21
    11:0.05
    Negative Logits
    )=(
    -1.96
    sbm
    -1.90
    soDeliveryDate
    -1.90
    quickShipAvailable
    -1.72
     rooft
    -1.70
     balcon
    -1.68
    SpaceEngineers
    -1.67
     desks
    -1.67
     diligent
    -1.65
     guiActiveUnfocused
    -1.62
    POSITIVE LOGITS
    bia
    2.03
     Detected
    1.99
    AIDS
    1.94
     Digest
    1.92
     virus
    1.83
     Virus
    1.75
    infect
    1.73
    cancer
    1.72
     Addiction
    1.72
     infection
    1.71
    Activations Density 0.001%

    No Known Activations