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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 13402
    Prev
    Next
    INDEX
    Explanations

    brief summaries or comparisons between multiple entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases indicating comparisons or similarities between multiple subjects

    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
    1:0.06
    2:0.23
    3:0.03
    4:0.02
    5:0.03
    6:0.18
    7:0.06
    8:0.06
    9:0.05
    10:0.05
    11:0.13
    Negative Logits
    selection
    -1.02
    cius
    -0.98
    ulia
    -0.97
     somewhere
    -0.96
    idan
    -0.88
    emer
    -0.88
    ciating
    -0.86
     spiral
    -0.83
    android
    -0.83
     Collider
    -0.82
    POSITIVE LOGITS
     acknowledges
    1.12
     sexes
    1.09
    NK
    0.99
     denies
    0.96
     begs
    0.96
    ieth
    0.95
    ":[{"
    0.94
     acknowledged
    0.90
    gate
    0.90
     wore
    0.90
    Activations Density 0.029%

    No Known Activations