© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 6677
    Prev
    Next
    INDEX
    Explanations

    phrases related to evidence and definitions, particularly in argumentative contexts

    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
    1:0.18
    2:0.04
    3:0.06
    4:0.02
    5:0.04
    6:0.17
    7:0.02
    8:0.02
    9:0.23
    10:0.03
    11:0.07
    Negative Logits
    ヤ
    -3.15
     Randolph
    -3.13
     Mitchell
    -3.06
     Vaughan
    -3.01
     Dahl
    -3.00
     Stella
    -2.98
     Nixon
    -2.96
    chev
    -2.93
     Patterson
    -2.90
    �
    -2.88
    POSITIVE LOGITS
    Based
    4.36
     based
    4.16
    based
    4.03
     Based
    3.93
    BF
    3.42
     bases
    3.21
     basis
    3.18
     independ
    3.15
    ASED
    3.10
     BS
    3.07
    Activations Density 0.004%

    No Known Activations