© 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. 19810
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to human health and physiological 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
    0:0.05
    1:0.04
    2:0.11
    3:0.03
    4:0.06
    5:0.03
    6:0.46
    7:0.04
    8:0.03
    9:0.03
    10:0.04
    11:0.03
    Negative Logits
    Weather
    -1.42
    Bench
    -1.33
     liner
    -1.31
    ipel
    -1.30
    Lens
    -1.28
     rotor
    -1.22
     biome
    -1.21
    Winged
    -1.21
     berth
    -1.21
     thermal
    -1.20
    POSITIVE LOGITS
    clus
    1.46
    oulos
    1.45
    usters
    1.39
     princ
    1.35
    ablishment
    1.35
    iatus
    1.33
    aukee
    1.33
    amaz
    1.32
    hof
    1.32
    aye
    1.32
    Activations Density 0.002%

    No Known Activations