© 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 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. 8759
    Prev
    Next
    INDEX
    Explanations

    references to Hamas and their activities

    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
    0:0.04
    1:0.03
    2:0.09
    3:0.18
    4:0.05
    5:0.11
    6:0.02
    7:0.05
    8:0.02
    9:0.02
    10:0.31
    11:0.02
    Negative Logits
     shortest
    -2.45
     Simpl
    -2.38
    mostly
    -2.37
     hardest
    -2.25
     simplicity
    -2.21
    surprisingly
    -2.18
     seldom
    -2.15
     mostly
    -2.12
     largely
    -2.02
     rarely
    -2.02
    POSITIVE LOGITS
     nor
    3.85
     or
    3.20
     whatsoever
    3.10
     either
    2.83
     anywhere
    2.80
    nor
    2.75
     any
    2.63
     anything
    2.52
     involvement
    2.50
     intervening
    2.43
    Activations Density 0.254%

    No Known Activations