© 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. 27303
    Prev
    Next
    INDEX
    Explanations

    terms related to various degrees of assault and murder charges

    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
    1:0.03
    2:0.19
    3:0.09
    4:0.07
    5:0.04
    6:0.09
    7:0.12
    8:0.04
    9:0.05
    10:0.10
    11:0.11
    Negative Logits
     wont
    -1.66
    DragonMagazine
    -1.65
    Downloadha
    -1.55
    nesday
    -1.52
    kinson
    -1.50
    tarians
    -1.50
    athi
    -1.48
    thouse
    -1.45
    ingen
    -1.44
    stud
    -1.41
    POSITIVE LOGITS
     understatement
    1.73
     immunity
    1.57
     commanding
    1.47
     honors
    1.45
     manslaughter
    1.40
     upkeep
    1.39
     liability
    1.37
     immortality
    1.36
     genetics
    1.30
     CPR
    1.29
    Activations Density 0.002%

    No Known Activations