© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43318
    Prev
    Next
    INDEX
    Explanations

    actions and regulations pertaining to individuals and their rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.01
    2:0.07
    3:0.13
    4:0.07
    5:0.04
    6:0.05
    7:0.05
    8:0.06
    9:0.07
    10:0.25
    11:0.10
    Negative Logits
     predecessor
    -1.57
     pecul
    -1.38
     Macro
    -1.34
     predecessors
    -1.34
     styl
    -1.31
    �士
    -1.30
     pse
    -1.29
     Style
    -1.26
     Orig
    -1.24
    MSN
    -1.23
    POSITIVE LOGITS
     safer
    1.68
     sue
    1.51
     healthier
    1.50
    paying
    1.45
     lawfully
    1.43
     harms
    1.43
    untary
    1.40
     boycot
    1.38
    untarily
    1.38
     safely
    1.37
    Activations Density 0.326%

    No Known Activations