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. 18747
    Prev
    Next
    INDEX
    Explanations

    formal governmental communication and official statements

    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
    0:0.14
    1:0.02
    2:0.16
    3:0.07
    4:0.03
    5:0.11
    6:0.04
    7:0.07
    8:0.20
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
     Glasgow
    -3.60
    inburgh
    -3.55
     NRL
    -3.27
     CFL
    -3.15
    onga
    -2.94
     arcade
    -2.93
     Edinburgh
    -2.90
     Sharks
    -2.89
    BIP
    -2.85
    ipeg
    -2.84
    POSITIVE LOGITS
     Abedin
    4.75
     Benghazi
    4.55
     Huma
    4.47
     diplomatic
    4.23
     Libya
    4.08
     Clinton
    4.05
     Diplom
    3.99
     diplomats
    3.97
     Rodham
    3.85
    Clinton
    3.79
    Activations Density 0.036%

    No Known Activations