© 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. 22625
    Prev
    Next
    INDEX
    Explanations

    references to dichotomies or opposing concepts

    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
    0:0.05
    1:0.42
    2:0.05
    3:0.03
    4:0.02
    5:0.02
    6:0.07
    7:0.09
    8:0.02
    9:0.03
    10:0.08
    11:0.06
    Negative Logits
     Loft
    -2.72
     dash
    -2.65
     Equal
    -2.47
    qual
    -2.46
     rises
    -2.44
     Transition
    -2.44
    ression
    -2.40
    aware
    -2.40
     escapes
    -2.36
     Yar
    -2.34
    POSITIVE LOGITS
     Hand
    7.41
    Hand
    7.34
     hand
    6.93
    hand
    6.16
     Hands
    4.87
     hands
    4.55
     handed
    4.33
    hands
    3.97
     palm
    3.79
     paw
    3.67
    Activations Density 0.059%

    No Known Activations