© 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. 10-ATT-KK
    11. 9320
    Prev
    Next
    INDEX
    Explanations

    incidents involving transportation accidents, particularly related to vehicles and airlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.02
    2:0.04
    3:0.05
    4:0.09
    5:0.13
    6:0.02
    7:0.06
    8:0.02
    9:0.36
    10:0.02
    11:0.04
    Negative Logits
     candid
    -2.33
     clinics
    -2.26
    types
    -2.22
    arios
    -2.21
     testim
    -2.15
     seminars
    -2.15
     professions
    -2.15
    umers
    -2.14
     publications
    -2.14
     assessments
    -2.13
    POSITIVE LOGITS
     collided
    4.66
     crashed
    4.58
     intercepted
    3.65
     ejected
    3.60
     sank
    3.58
     derailed
    3.58
     detonated
    3.54
     drifted
    3.49
     sailed
    3.48
     downed
    3.40
    Activations Density 0.450%

    No Known Activations