© 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. 10-ATT-KK
    11. 13685
    Prev
    Next
    INDEX
    Explanations

    content related to legal issues and ethical discussions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.03
    2:0.06
    3:0.03
    4:0.02
    5:0.02
    6:0.04
    7:0.12
    8:0.02
    9:0.04
    10:0.49
    11:0.03
    Negative Logits
     peas
    -2.79
     Celt
    -2.60
     Democr
    -2.58
    Whe
    -2.58
     Julio
    -2.56
     nerv
    -2.51
     Forsaken
    -2.50
    pes
    -2.46
     mul
    -2.41
     marg
    -2.39
    POSITIVE LOGITS
     K
    10.62
    K
    7.86
     KL
    5.80
    k
    5.54
    krit
    5.49
     k
    5.32
     KH
    5.05
     KM
    5.03
     KP
    4.55
     KR
    4.49
    Activations Density 0.176%

    No Known Activations