© 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. 5-ATT-KK
    11. 5468
    Prev
    Next
    INDEX
    Explanations

    references to attacks or discussions involving attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.01
    2:0.07
    3:0.06
    4:0.05
    5:0.03
    6:0.16
    7:0.18
    8:0.04
    9:0.04
    10:0.19
    11:0.10
    Negative Logits
    redo
    -1.39
    TRY
    -1.37
     proud
    -1.37
    OY
    -1.35
    bourg
    -1.32
     supervised
    -1.27
     checkout
    -1.26
     trim
    -1.25
     yacht
    -1.23
     groove
    -1.23
    POSITIVE LOGITS
     attacks
    1.71
     hoax
    1.66
     Attacks
    1.64
     behavi
    1.61
     bombings
    1.58
     undermin
    1.57
    hate
    1.56
     WATCHED
    1.52
    attacks
    1.51
     unbeliev
    1.50
    Activations Density 0.002%

    No Known Activations