© 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. 5637
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate actions or relationships involving "to" and "or" in various contexts

    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
    0:0.04
    1:0.26
    2:0.04
    3:0.15
    4:0.06
    5:0.05
    6:0.06
    7:0.06
    8:0.03
    9:0.07
    10:0.08
    11:0.04
    Negative Logits
     Overall
    -2.47
     overall
    -2.38
     Lastly
    -2.32
     misinformation
    -2.25
     Additionally
    -2.24
     Together
    -2.19
     messenger
    -2.13
     Totem
    -2.09
     McGee
    -2.09
     However
    -2.06
    POSITIVE LOGITS
     fifteen
    3.25
    six
    3.04
    five
    3.03
     fourteen
    3.00
    ires
    2.97
    undred
    2.96
    eight
    2.96
    ifty
    2.95
     twent
    2.95
    abytes
    2.81
    Activations Density 0.010%

    No Known Activations