© 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. 3-ATT-KK
    11. 13066
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to international relations and conflicts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    modal verbs indicating capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.06
    2:0.07
    3:0.04
    4:0.02
    5:0.10
    6:0.05
    7:0.05
    8:0.07
    9:0.19
    10:0.06
    11:0.22
    Negative Logits
    CI
    -1.82
    ensor
    -1.61
    RP
    -1.60
    ongo
    -1.52
    susp
    -1.49
    PI
    -1.45
    arbon
    -1.45
    onen
    -1.42
    cult
    -1.42
    ו
    -1.36
    POSITIVE LOGITS
     anymore
    1.88
     nor
    1.62
    numbered
    1.57
     survives
    1.50
     bothered
    1.44
     predec
    1.44
     Horses
    1.43
     spared
    1.42
     elig
    1.42
    itled
    1.41
    Activations Density 0.010%

    No Known Activations