© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 21029
    Prev
    Next
    INDEX
    Explanations

    specific details and references related to political and legal contexts

    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
    0:0.07
    1:0.03
    2:0.08
    3:0.25
    4:0.05
    5:0.09
    6:0.03
    7:0.07
    8:0.06
    9:0.02
    10:0.11
    11:0.09
    Negative Logits
    entimes
    -2.42
    arre
    -2.26
    yne
    -2.24
     differs
    -2.13
    vari
    -2.12
    agonists
    -2.07
    ptoms
    -2.06
    enes
    -2.06
    ria
    -2.03
     reacts
    -2.02
    POSITIVE LOGITS
     priceless
    2.35
     billions
    2.17
     bona
    2.10
     AMERICA
    2.09
     goddamn
    2.07
     bragging
    2.05
     untold
    2.03
     Abbott
    2.03
     trillions
    1.97
     royalty
    1.96
    Activations Density 1.109%

    No Known Activations