© 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. 9-ATT-KK
    11. 6315
    Prev
    Next
    INDEX
    Explanations

    instances of conditional or hypothetical language within a political or evaluative context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.09
    1:0.03
    2:0.09
    3:0.04
    4:0.07
    5:0.04
    6:0.22
    7:0.05
    8:0.08
    9:0.20
    10:0.03
    11:0.03
    Negative Logits
    intendo
    -3.90
    onga
    -3.66
    76561
    -3.63
    iba
    -3.60
    windows
    -3.59
    razil
    -3.45
     swim
    -3.43
     Chess
    -3.41
     swimming
    -3.40
    bj
    -3.36
    POSITIVE LOGITS
     Lerner
    10.17
     Lambert
    8.76
     Coulter
    4.76
     Scully
    4.73
     Levin
    4.73
     Lois
    4.58
     McCarthy
    4.42
     Villa
    4.38
     Mercer
    4.24
     Lisa
    4.23
    Activations Density 0.001%

    No Known Activations