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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 116
    Prev
    Next
    INDEX
    Explanations

    phrases related to complaints and allegations

    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
    0:0.07
    1:0.05
    2:0.07
    3:0.07
    4:0.04
    5:0.05
    6:0.04
    7:0.06
    8:0.34
    9:0.05
    10:0.04
    11:0.05
    Negative Logits
    Palest
    -3.53
     Vatican
    -3.36
     Palestinian
    -3.15
     Palest
    -3.09
     Rabb
    -3.08
     Palestine
    -2.99
    ć
    -2.99
     Congo
    -2.97
    ijn
    -2.90
     Palestinians
    -2.90
    POSITIVE LOGITS
     Winnipeg
    3.58
     Calgary
    3.28
    ifax
    3.24
     Labrador
    3.10
     Darwin
    3.10
     Halifax
    3.00
     Goose
    2.96
     Edmonton
    2.95
     Newfoundland
    2.94
     Bour
    2.89
    Activations Density 0.004%

    No Known Activations