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. 9-ATT-KK
    6. 18742
    Prev
    Next
    INDEX
    Explanations

    verbs indicating the presence of systems, actions, or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.04
    2:0.05
    3:0.19
    4:0.03
    5:0.06
    6:0.02
    7:0.05
    8:0.04
    9:0.02
    10:0.37
    11:0.02
    Negative Logits
    until
    -3.00
     anymore
    -2.56
     until
    -2.33
    etheless
    -2.32
     forever
    -2.28
     unless
    -2.27
    ogether
    -2.25
     anytime
    -2.23
    ��
    -2.21
    none
    -2.17
    POSITIVE LOGITS
     occasional
    2.31
     prominently
    2.22
    senal
    2.18
     specials
    1.85
     occasionally
    1.81
     glimps
    1.81
     extensively
    1.81
     HW
    1.77
     trademarks
    1.77
     cameo
    1.73
    Activations Density 0.271%

    No Known Activations