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

    Neuronpedia

    APICircuit 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. 7665
    Prev
    Next
    INDEX
    Explanations

    phrases related to questions and inquiry

    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
    0:0.12
    1:0.04
    2:0.10
    3:0.06
    4:0.07
    5:0.04
    6:0.16
    7:0.05
    8:0.04
    9:0.20
    10:0.03
    11:0.03
    Negative Logits
     resistor
    -3.46
     dan
    -3.43
    mask
    -3.42
    aber
    -3.38
    igers
    -3.25
     Rider
    -3.23
    Mask
    -3.13
    icides
    -3.12
     Rebel
    -3.08
    acer
    -3.06
    POSITIVE LOGITS
     Whole
    7.76
     Pilgrim
    4.59
     grocer
    4.52
     Kro
    4.39
     grocery
    4.37
     Walmart
    4.18
     Whale
    4.15
     Macy
    4.06
     Costco
    3.87
     Trader
    3.67
    Activations Density 0.002%

    No Known Activations