© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 39730
    Prev
    Next
    INDEX
    Explanations

    questions and phrases suggesting choice or decision-making

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.07
    1:0.09
    2:0.03
    3:0.04
    4:0.03
    5:0.32
    6:0.03
    7:0.02
    8:0.08
    9:0.08
    10:0.10
    11:0.05
    Negative Logits
    growth
    -1.65
    flies
    -1.54
    growing
    -1.51
    library
    -1.50
     epidemic
    -1.37
    abies
    -1.33
    ukemia
    -1.32
    sets
    -1.31
    translation
    -1.31
     Virus
    -1.30
    POSITIVE LOGITS
     abst
    2.06
    isSpecialOrderable
    1.97
    endment
    1.86
     defer
    1.74
    displayText
    1.74
    agall
    1.69
     Pledge
    1.67
    Option
    1.64
     answ
    1.64
     bribe
    1.64
    Activations Density 0.205%

    No Known Activations