© 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. 9-ATT-KK
    11. 16095
    Prev
    Next
    INDEX
    Explanations

    instances of influential recommendations and endorsements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.02
    2:0.08
    3:0.04
    4:0.06
    5:0.06
    6:0.17
    7:0.07
    8:0.10
    9:0.21
    10:0.03
    11:0.04
    Negative Logits
     Sev
    -3.88
     XV
    -3.71
     Severus
    -3.70
     Sorceress
    -3.55
     Sas
    -3.53
    resy
    -3.38
     Vict
    -3.37
     SG
    -3.37
    stan
    -3.16
     Armenian
    -3.12
    POSITIVE LOGITS
    Bloomberg
    9.57
     Bloomberg
    9.42
     Blasio
    4.70
     Giuliani
    4.39
     Carney
    4.22
     Camden
    4.07
     Bernstein
    3.94
     Krugman
    3.80
     Miliband
    3.76
     Barclays
    3.73
    Activations Density 0.007%

    No Known Activations