© 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. 10-ATT-KK
    11. 6633
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and matters of defamation

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.04
    1:0.05
    2:0.07
    3:0.03
    4:0.02
    5:0.01
    6:0.04
    7:0.09
    8:0.03
    9:0.03
    10:0.51
    11:0.03
    Negative Logits
    aining
    -3.00
    thood
    -2.97
     mal
    -2.84
    usra
    -2.82
    itiz
    -2.76
    grain
    -2.65
    dl
    -2.63
    Interstitial
    -2.63
    tal
    -2.63
    tt
    -2.62
    POSITIVE LOGITS
     E
    10.45
    E
    8.20
     EB
    5.98
     e
    5.93
     Eb
    4.98
    EH
    4.89
    Es
    4.88
     EF
    4.83
    EE
    4.81
     Es
    4.75
    Activations Density 0.347%

    No Known Activations