© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 2543
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about complicated subjects

    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
    0:0.02
    1:0.04
    2:0.12
    3:0.06
    4:0.08
    5:0.08
    6:0.04
    7:0.08
    8:0.04
    9:0.03
    10:0.31
    11:0.05
    Negative Logits
     firsthand
    -2.50
    estial
    -2.38
     successes
    -2.33
     nightly
    -2.31
    externalActionCode
    -2.30
     redeem
    -2.27
     redeemed
    -2.25
     rehabilit
    -2.21
     marrow
    -2.12
     healed
    -2.11
    POSITIVE LOGITS
    Because
    3.24
     Why
    3.16
     Because
    3.09
    why
    3.04
    Why
    2.91
    because
    2.86
     fearing
    2.58
     Wouldn
    2.56
     because
    2.55
     bothering
    2.55
    Activations Density 0.029%

    No Known Activations