© 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. 9-ATT-KK
    11. 17749
    Prev
    Next
    INDEX
    Explanations

    information related to vehicle safety recalls and defects

    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
    0:0.11
    1:0.05
    2:0.12
    3:0.08
    4:0.07
    5:0.06
    6:0.08
    7:0.07
    8:0.08
    9:0.07
    10:0.06
    11:0.08
    Negative Logits
    20439
    -3.18
     Peck
    -3.10
    Torrent
    -2.99
     Hare
    -2.90
     Rhod
    -2.67
     Shadow
    -2.66
     Torch
    -2.65
    ��
    -2.63
     quar
    -2.56
    Shadow
    -2.46
    POSITIVE LOGITS
     infl
    3.33
    LM
    2.85
    heim
    2.79
     LO
    2.63
    heed
    2.55
     unbel
    2.50
    oiler
    2.49
    enegger
    2.48
     foam
    2.48
    bags
    2.48
    Activations Density 0.001%

    No Known Activations