© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 10730
    Prev
    Next
    INDEX
    Explanations

    elements of discourse or punctuation indicating pauses and emphasized 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
    0:0.02
    1:0.03
    2:0.22
    3:0.02
    4:0.02
    5:0.05
    6:0.14
    7:0.16
    8:0.11
    9:0.06
    10:0.05
    11:0.07
    Negative Logits
     antidote
    -1.06
     Plays
    -1.04
    reci
    -1.02
    CV
    -1.00
    Pros
    -1.00
    past
    -0.99
     warranties
    -0.99
    mes
    -0.99
     Videos
    -0.98
    pins
    -0.97
    POSITIVE LOGITS
    isphere
    1.40
    oire
    1.22
     Lamar
    1.16
     Kron
    1.15
     Khalid
    1.15
     Kraken
    1.13
    afia
    1.12
    arger
    1.11
     Guinness
    1.11
     Lanka
    1.09
    Activations Density 0.033%

    No Known Activations