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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 44160
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to organizations and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.23
    2:0.04
    3:0.04
    4:0.04
    5:0.23
    6:0.04
    7:0.02
    8:0.05
    9:0.07
    10:0.08
    11:0.05
    Negative Logits
    rossover
    -1.91
    opus
    -1.87
    yg
    -1.83
    cookie
    -1.78
    lycer
    -1.75
    kees
    -1.75
    ipel
    -1.74
    spir
    -1.73
    enario
    -1.72
    ril
    -1.70
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    2.41
    Alert
    1.83
    Austin
    1.80
    manship
    1.78
     Americas
    1.70
     Aware
    1.68
     organisation
    1.67
     Austral
    1.64
     Nova
    1.63
     Ern
    1.59
    Activations Density 0.002%

    No Known Activations