© 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. 9-ATT-KK
    11. 22403
    Prev
    Next
    INDEX
    Explanations

    events related to accidents and collisions, particularly those involving vehicles or aircraft

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.02
    2:0.06
    3:0.18
    4:0.02
    5:0.13
    6:0.02
    7:0.08
    8:0.03
    9:0.02
    10:0.31
    11:0.03
    Negative Logits
     heirs
    -2.00
     anymore
    -1.95
     recourse
    -1.94
     flashbacks
    -1.92
     histories
    -1.91
     reun
    -1.90
     rematch
    -1.85
     assurances
    -1.84
     reminders
    -1.82
     explanations
    -1.78
    POSITIVE LOGITS
     incorrectly
    2.72
     mistakenly
    2.68
     errone
    2.21
     accidentally
    2.20
     prematurely
    2.08
     wrongly
    2.04
     unintentionally
    2.04
     inadvertently
    2.02
     improperly
    2.01
     injuring
    1.95
    Activations Density 0.213%

    No Known Activations