© 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. 28002
    Prev
    Next
    INDEX
    Explanations

    references to being pulled over by police in various contexts

    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
    1:0.00
    2:0.05
    3:0.04
    4:0.09
    5:0.03
    6:0.03
    7:0.34
    8:0.02
    9:0.04
    10:0.23
    11:0.05
    Negative Logits
    bern
    -1.78
    inness
    -1.78
    izons
    -1.76
    roud
    -1.73
    yss
    -1.72
    uble
    -1.69
    vana
    -1.67
     brim
    -1.65
    vor
    -1.63
    rss
    -1.62
    POSITIVE LOGITS
     revocation
    1.84
     roadside
    1.78
     unethical
    1.74
     Illegal
    1.64
     violating
    1.63
     negligent
    1.62
     violates
    1.60
     Spy
    1.60
     Craigslist
    1.59
     expired
    1.56
    Activations Density 0.002%

    No Known Activations