© 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. 17067
    Prev
    Next
    INDEX
    Explanations

    instances of significant actions or statements related to situational updates or events

    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
    0:0.17
    1:0.18
    2:0.05
    3:0.04
    4:0.03
    5:0.02
    6:0.06
    7:0.15
    8:0.02
    9:0.04
    10:0.15
    11:0.05
    Negative Logits
    �
    -2.90
    atche
    -2.81
    �
    -2.80
    �
    -2.71
     thrott
    -2.67
    �
    -2.63
    �
    -2.63
     VO
    -2.61
    interstitial
    -2.57
    Yang
    -2.55
    POSITIVE LOGITS
     Moss
    8.13
     moss
    3.99
     Morton
    3.47
     Ness
    3.04
     Hezbollah
    2.95
     mushroom
    2.92
     Mushroom
    2.90
    mons
    2.89
     Dru
    2.86
    oss
    2.86
    Activations Density 0.005%

    No Known Activations