© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 35370
    Prev
    Next
    INDEX
    Explanations

    expressions of minimizing or downplaying significant issues or threats

    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
    1:0.01
    2:0.05
    3:0.08
    4:0.20
    5:0.02
    6:0.04
    7:0.37
    8:0.02
    9:0.03
    10:0.06
    11:0.04
    Negative Logits
    arnaev
    -1.98
    stown
    -1.76
    outheastern
    -1.68
    orers
    -1.68
    unda
    -1.61
    kefeller
    -1.61
    strate
    -1.60
    inals
    -1.60
    ebook
    -1.58
    redo
    -1.58
    POSITIVE LOGITS
     severity
    1.91
     inacc
    1.86
     prevalence
    1.74
     underestimate
    1.69
     inaccur
    1.66
     seriousness
    1.65
     provocation
    1.62
     unbeliev
    1.62
     exagger
    1.61
     motives
    1.61
    Activations Density 0.002%

    No Known Activations