© 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. 33336
    Prev
    Next
    INDEX
    Explanations

    instances of people and their actions, particularly related to politics and stories

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.02
    1:0.01
    2:0.31
    3:0.13
    4:0.12
    5:0.03
    6:0.06
    7:0.07
    8:0.06
    9:0.04
    10:0.07
    11:0.04
    Negative Logits
    ilities
    -1.87
    ommod
    -1.66
    izons
    -1.55
    emn
    -1.43
     hemor
    -1.43
    illusion
    -1.42
    ustomed
    -1.42
    ][/
    -1.41
    effic
    -1.40
    imony
    -1.39
    POSITIVE LOGITS
    AZ
    1.67
     belonged
    1.64
    方
    1.58
     Pwr
    1.53
    daq
    1.53
    �
    1.50
     belongs
    1.49
    liest
    1.47
    cro
    1.44
    ּ
    1.44
    Activations Density 0.019%

    No Known Activations