© 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. 23302
    Prev
    Next
    INDEX
    Explanations

    references to screen resolution and display settings

    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
    0:0.07
    1:0.14
    2:0.08
    3:0.06
    4:0.04
    5:0.03
    6:0.05
    7:0.09
    8:0.11
    9:0.04
    10:0.15
    11:0.08
    Negative Logits
     sem
    -3.00
    eson
    -2.68
     verte
    -2.65
    ussen
    -2.58
     suites
    -2.55
     sor
    -2.49
     agre
    -2.44
     herb
    -2.42
     harness
    -2.40
     Rig
    -2.34
    POSITIVE LOGITS
    facing
    3.07
    1920
    2.96
     PNG
    2.75
     2048
    2.73
     1920
    2.71
     IPS
    2.71
    FACE
    2.55
    IPS
    2.53
    2020
    2.48
    pixel
    2.47
    Activations Density 0.000%

    No Known Activations