© 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. 38039
    Prev
    Next
    INDEX
    Explanations

    instances of people expressing skepticism or criticism of political figures or events

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.06
    3:0.10
    4:0.06
    5:0.04
    6:0.04
    7:0.12
    8:0.05
    9:0.08
    10:0.10
    11:0.23
    Negative Logits
     Gaw
    -1.64
     Hav
    -1.63
     Salvation
    -1.61
     YPG
    -1.58
     Ottoman
    -1.56
     Anglic
    -1.55
     PSP
    -1.54
     Pesh
    -1.54
     Unity
    -1.53
     FM
    -1.53
    POSITIVE LOGITS
    ォ
    1.95
    ��
    1.69
    livious
    1.67
    cffff
    1.66
    ortment
    1.61
    eport
    1.60
    ourke
    1.60
     EVs
    1.57
    ertodd
    1.57
    iper
    1.56
    Activations Density 0.001%

    No Known Activations