© 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. 2-ATT-KK
    11. 22639
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially related to political figures and specific organizations

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

    references to pointing or directing attention towards specific subjects or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.02
    2:0.11
    3:0.06
    4:0.06
    5:0.06
    6:0.04
    7:0.03
    8:0.33
    9:0.13
    10:0.05
    11:0.02
    Negative Logits
    conservancy
    -1.22
    soever
    -1.21
    roy
    -1.20
    interstitial
    -1.18
     repaired
    -1.15
    emouth
    -1.08
    sembly
    -1.08
    ashington
    -1.08
     grapp
    -1.06
    lymp
    -1.06
    POSITIVE LOGITS
    dial
    1.31
     Genocide
    1.22
    zinski
    1.20
     causation
    1.14
    TextColor
    1.11
     veto
    1.11
     flashing
    1.10
    enance
    1.09
    azar
    1.09
    urai
    1.07
    Activations Density 0.046%

    No Known Activations