© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14411
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or changes

    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
    1:0.14
    2:0.05
    3:0.11
    4:0.05
    5:0.07
    6:0.04
    7:0.26
    8:0.03
    9:0.07
    10:0.03
    11:0.04
    Negative Logits
     Bulgar
    -2.90
    Qual
    -2.57
    Quant
    -2.42
    ches
    -2.40
    Austral
    -2.30
    Modern
    -2.22
    aturday
    -2.21
     lifts
    -2.20
     Palest
    -2.17
    unal
    -2.16
    POSITIVE LOGITS
     Troll
    2.76
     Gawker
    2.73
     droid
    2.66
     Sage
    2.60
     Mouth
    2.59
    wrapper
    2.58
     Chaser
    2.44
    cia
    2.36
     Gree
    2.34
    sword
    2.34
    Activations Density 0.001%

    No Known Activations