© 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. 5522
    Prev
    Next
    INDEX
    Explanations

    interrogative statements and quotes

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.04
    1:0.06
    2:0.03
    3:0.07
    4:0.30
    5:0.08
    6:0.07
    7:0.07
    8:0.04
    9:0.05
    10:0.04
    11:0.09
    Negative Logits
    alach
    -2.68
     "$:/
    -2.58
    edom
    -2.58
    onut
    -2.55
    ;;;;;;;;;;;;
    -2.52
    ptives
    -2.50
     Melania
    -2.44
    ��
    -2.44
    thood
    -2.39
    avorite
    -2.38
    POSITIVE LOGITS
    Q
    4.80
     Q
    4.18
    JV
    3.37
    RW
    3.34
    JJ
    3.25
     AQ
    3.11
    q
    2.99
    JA
    2.95
    DB
    2.94
    Hi
    2.94
    Activations Density 0.008%

    No Known Activations