© 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. 16799
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and strong contrasts

    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
    0:0.12
    1:0.09
    2:0.15
    3:0.06
    4:0.03
    5:0.01
    6:0.07
    7:0.10
    8:0.03
    9:0.03
    10:0.21
    11:0.03
    Negative Logits
     Romanian
    -3.43
     Grizz
    -3.34
    tsky
    -3.33
    Pont
    -3.08
     Ghostbusters
    -2.93
     Romania
    -2.88
    zinski
    -2.87
     Miz
    -2.82
    ンジ
    -2.80
     Micha
    -2.75
    POSITIVE LOGITS
     AL
    9.31
    AL
    6.44
     ALE
    5.27
     CAL
    5.10
     SAL
    5.05
     AB
    4.64
    ALT
    4.47
     NL
    4.43
    Al
    4.37
     AH
    4.26
    Activations Density 0.004%

    No Known Activations