© 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. 38379
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal and political contexts

    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
    0:0.02
    1:0.03
    2:0.07
    3:0.16
    4:0.15
    5:0.03
    6:0.25
    7:0.05
    8:0.04
    9:0.04
    10:0.07
    11:0.04
    Negative Logits
    hend
    -1.66
    nesday
    -1.39
     ourselves
    -1.38
    phrine
    -1.37
     yourselves
    -1.34
    uador
    -1.33
    …]
    -1.33
     escalate
    -1.30
    that
    -1.29
    those
    -1.29
    POSITIVE LOGITS
    comings
    1.67
    juries
    1.54
     predecessors
    1.43
    シ
    1.39
     stature
    1.38
    folio
    1.38
     counterpart
    1.37
    ancies
    1.36
     counterparts
    1.35
    シャ
    1.34
    Activations Density 0.012%

    No Known Activations