© 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. 8279
    Prev
    Next
    INDEX
    Explanations

    terms and patterns related to ease and simplicity in doing things

    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
    0:0.06
    1:0.05
    2:0.08
    3:0.05
    4:0.04
    5:0.04
    6:0.15
    7:0.04
    8:0.04
    9:0.32
    10:0.04
    11:0.04
    Negative Logits
     Hanson
    -3.82
    OWS
    -3.65
     Hus
    -3.61
    govtrack
    -3.38
    CHA
    -3.37
    ZA
    -3.27
    CLASS
    -3.23
    allah
    -3.19
     Cream
    -3.14
     Huma
    -3.14
    POSITIVE LOGITS
     ret
    7.83
    ret
    7.10
    Ret
    6.91
     Ret
    6.84
     RET
    5.26
     retina
    5.01
     retri
    4.80
    rets
    4.74
     Retro
    4.42
     retract
    4.28
    Activations Density 0.002%

    No Known Activations