© 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. 5-ATT-KK
    11. 2661
    Prev
    Next
    INDEX
    Explanations

    words associated with causation, particularly in relation to physical or health conditions

    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
    0:0.02
    1:0.02
    2:0.06
    3:0.05
    4:0.08
    5:0.03
    6:0.04
    7:0.39
    8:0.02
    9:0.03
    10:0.12
    11:0.09
    Negative Logits
    maid
    -1.84
    ustomed
    -1.80
     reassured
    -1.55
    pared
    -1.53
    erning
    -1.51
    ournal
    -1.50
    artisan
    -1.50
    �
    -1.47
    �
    -1.45
    cript
    -1.44
    POSITIVE LOGITS
     disturbance
    1.94
     disturbances
    1.91
     crashes
    1.90
     illness
    1.79
     poisoning
    1.73
     trouble
    1.71
     wreckage
    1.71
     Damage
    1.70
     damage
    1.68
     sickness
    1.66
    Activations Density 0.014%

    No Known Activations