© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 12574
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.08
    2:0.08
    3:0.08
    4:0.02
    5:0.07
    6:0.06
    7:0.06
    8:0.10
    9:0.14
    10:0.11
    11:0.04
    Negative Logits
    ensional
    -1.42
    dfx
    -1.32
    rikes
    -1.28
    ishops
    -1.28
     repeated
    -1.25
    ilings
    -1.24
    umann
    -1.23
    cv
    -1.21
     ----------------------------------------------------------------
    -1.20
    chio
    -1.19
    POSITIVE LOGITS
     strives
    1.53
    ヘ
    1.34
     Presents
    1.32
    �
    1.32
    Champ
    1.32
     reservation
    1.31
    ゼ
    1.31
     Fiesta
    1.30
    Asset
    1.27
    Includes
    1.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.