© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 15193
    Prev
    Next
    INDEX
    Explanations

    mentions of negligence and manslaughter in a narrative context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.03
    2:0.17
    3:0.07
    4:0.08
    5:0.08
    6:0.03
    7:0.04
    8:0.07
    9:0.20
    10:0.07
    11:0.03
    Negative Logits
    rir
    -1.96
    soDeliveryDate
    -1.62
    icol
    -1.47
    anian
    -1.28
     enthusi
    -1.28
    kefeller
    -1.27
    龍喚士
    -1.26
    yip
    -1.26
    sav
    -1.25
    illac
    -1.25
    POSITIVE LOGITS
     manslaughter
    1.49
     negligence
    1.35
     adjud
    1.34
     §§
    1.30
     negligent
    1.26
    charges
    1.22
     §
    1.21
     Malf
    1.21
     improper
    1.21
    uly
    1.19
    Activations Density 0.003%

    No Known Activations