© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22737
    Prev
    Next
    INDEX
    Explanations

    capitalized non-English words

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    specific characters or symbols, particularly in a foreign language context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.02
    2:0.14
    3:0.07
    4:0.09
    5:0.09
    6:0.04
    7:0.04
    8:0.16
    9:0.10
    10:0.09
    11:0.03
    Negative Logits
    aird
    -1.20
     Thumbnails
    -1.18
    orkshire
    -1.16
    pherd
    -1.16
    omez
    -1.14
     Suarez
    -1.09
     Dispatch
    -1.07
    gdala
    -1.07
    Dispatch
    -1.06
    ettings
    -1.04
    POSITIVE LOGITS
     curtain
    1.04
     drums
    1.03
    κ
    1.03
     aisle
    1.02
     hyster
    1.00
     tires
    0.98
    γ
    0.98
    ceived
    0.95
    π
    0.95
     pedals
    0.94
    Activations Density 0.003%

    No Known Activations