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

    Neuronpedia

    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. 43911
    Prev
    Next
    INDEX
    Explanations

    references to legal actions and offenses

    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
    1:0.02
    2:0.05
    3:0.06
    4:0.33
    5:0.03
    6:0.05
    7:0.22
    8:0.03
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
     appealed
    -1.48
     summoned
    -1.42
    tis
    -1.39
     chrom
    -1.38
     adjusts
    -1.35
     commissioner
    -1.34
    oyer
    -1.33
     outwe
    -1.30
    inventoryQuantity
    -1.29
     tempered
    -1.29
    POSITIVE LOGITS
    DEC
    1.56
    panic
    1.48
    mington
    1.48
    ength
    1.46
     ACTIONS
    1.45
    appropriately
    1.43
    wikipedia
    1.39
    ateral
    1.37
    neg
    1.33
    interstitial
    1.32
    Activations Density 0.006%

    No Known Activations