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. 3-ATT-KK
    6. 7644
    Prev
    Next
    INDEX
    Explanations

    significant or notable elements within various contexts, such as outstanding parts, stories, and key phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.03
    2:0.31
    3:0.03
    4:0.02
    5:0.02
    6:0.27
    7:0.04
    8:0.04
    9:0.03
    10:0.04
    11:0.07
    Negative Logits
    leigh
    -1.76
    Ly
    -1.39
     Badge
    -1.30
    oney
    -1.29
     Rye
    -1.28
    ished
    -1.26
     Cruise
    -1.25
     Junk
    -1.25
     Kitty
    -1.25
     Lack
    -1.24
    POSITIVE LOGITS
     embr
    1.59
     disapp
    1.59
    emies
    1.52
     pioneers
    1.50
     distingu
    1.49
    agonists
    1.46
     undermin
    1.44
     manif
    1.42
    ilings
    1.40
    arters
    1.39
    Activations Density 0.087%

    No Known Activations