© 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. 21480
    Prev
    Next
    INDEX
    Explanations

    specific numeric values or characters in a sequence

    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
    0:0.09
    1:0.03
    2:0.22
    3:0.04
    4:0.04
    5:0.03
    6:0.03
    7:0.13
    8:0.04
    9:0.04
    10:0.23
    11:0.03
    Negative Logits
     SM
    -3.08
     Marlins
    -3.07
     MU
    -3.02
     Ler
    -2.88
    CHAT
    -2.84
     triglycer
    -2.79
     ST
    -2.76
     TF
    -2.73
     Mak
    -2.73
    ¯
    -2.71
    POSITIVE LOGITS
    uthor
    3.52
    xb
    3.37
    aido
    3.37
    aeda
    3.10
    Rh
    3.06
    xa
    2.89
    bd
    2.81
    rimination
    2.77
    ennis
    2.75
    xc
    2.72
    Activations Density 0.001%

    No Known Activations