© 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. 10774
    Prev
    Next
    INDEX
    Explanations

    specific references to names and organizations related to events or articles

    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
    1:0.03
    2:0.04
    3:0.05
    4:0.40
    5:0.07
    6:0.03
    7:0.06
    8:0.09
    9:0.06
    10:0.02
    11:0.04
    Negative Logits
    !",
    -3.03
    "-
    -2.85
    "?
    -2.68
    ";
    -2.55
    ?",
    -2.47
    "!
    -2.46
     ",
    -2.36
    '';
    -2.31
    ;"
    -2.25
     (?,
    -2.25
    POSITIVE LOGITS
     Caption
    2.80
     Image
    2.47
     Picture
    2.30
    �
    2.26
    photo
    2.24
    }:
    2.23
    �
    2.21
    ').
    2.20
     Symbol
    2.16
    advertising
    2.16
    Activations Density 0.005%

    No Known Activations