© 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. 22845
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to news articles

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

    instances of the word "some" in various contexts

    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
    0:0.11
    1:0.07
    2:0.07
    3:0.18
    4:0.04
    5:0.07
    6:0.08
    7:0.03
    8:0.04
    9:0.12
    10:0.11
    11:0.04
    Negative Logits
    ariat
    -1.28
     inflic
    -1.19
    SHARE
    -1.18
    izont
    -1.18
    untarily
    -1.14
    Scotland
    -1.13
     Shutterstock
    -1.13
    enegger
    -1.11
    byss
    -1.10
     Natasha
    -1.10
    POSITIVE LOGITS
     surprises
    1.46
     caveats
    1.38
     acron
    1.37
     dudes
    1.30
     similarities
    1.27
     wrinkles
    1.27
     explanations
    1.26
     weird
    1.26
     flavors
    1.24
     flavours
    1.22
    Activations Density 0.142%

    No Known Activations