Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10367
    Prev
    Next
    INDEX
    Explanations

    interrogative words and phrases, particularly questions or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.03
    2:0.12
    3:0.13
    4:0.01
    5:0.03
    6:0.04
    7:0.10
    8:0.06
    9:0.19
    10:0.10
    11:0.13
    Negative Logits
    hement
    -1.41
    eries
    -1.34
    geoning
    -1.32
    uably
    -1.30
    vir
    -1.28
    renched
    -1.25
    alia
    -1.19
    raught
    -1.18
    pmwiki
    -1.17
    rolled
    -1.17
    POSITIVE LOGITS
     anymore
    1.50
     behavi
    1.29
     newsp
    1.24
     terminology
    1.23
     myself
    1.22
     nor
    1.16
     whereabouts
    1.15
     Palestin
    1.15
     explan
    1.12
     Doodle
    1.11
    Activations Density 0.033%

    No Known Activations