© 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. 2-ATT-KK
    11. 22687
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly related to incidents or events

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

    names and references related to individuals 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
    0:0.06
    1:0.04
    2:0.30
    3:0.07
    4:0.08
    5:0.05
    6:0.05
    7:0.04
    8:0.05
    9:0.10
    10:0.07
    11:0.03
    Negative Logits
     citiz
    -1.59
    etheless
    -1.47
     grunt
    -1.20
     eleph
    -1.16
    uracy
    -1.16
    pection
    -1.14
    noon
    -1.14
     tremend
    -1.14
    ircraft
    -1.12
    llah
    -1.12
    POSITIVE LOGITS
    gaard
    1.31
    inen
    1.28
    iasco
    1.20
    ophy
    1.19
    bye
    1.19
     Keys
    1.19
     Brothers
    1.17
    zes
    1.16
    offer
    1.15
     toes
    1.15
    Activations Density 0.001%

    No Known Activations