© 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. 5-ATT-KK
    11. 27898
    Prev
    Next
    INDEX
    Explanations

    references to the concepts of protection and prevention related to people and their actions

    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
    0:0.02
    1:0.02
    2:0.05
    3:0.13
    4:0.37
    5:0.04
    6:0.04
    7:0.12
    8:0.03
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
     Rohing
    -1.82
     Airl
    -1.51
     unden
    -1.47
     Wheels
    -1.45
     advoc
    -1.41
     lil
    -1.41
     Ashton
    -1.40
    forums
    -1.37
    :{
    -1.37
    �
    -1.35
    POSITIVE LOGITS
     harm
    1.73
     undue
    1.70
     adversely
    1.62
     harmful
    1.62
     avoidance
    1.61
     future
    1.60
    ividual
    1.60
     altogether
    1.48
     discriminating
    1.47
     falsely
    1.47
    Activations Density 0.067%

    No Known Activations