© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 8117
    Prev
    Next
    INDEX
    Explanations

    references to app installations and configurations

    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
    0:0.10
    1:0.09
    2:0.07
    3:0.06
    4:0.15
    5:0.07
    6:0.08
    7:0.07
    8:0.06
    9:0.06
    10:0.06
    11:0.07
    Negative Logits
     ingred
    -1.73
     proble
    -1.55
    lopp
    -1.54
    BuyableInstoreAndOnline
    -1.43
     Mechanical
    -1.36
    ograp
    -1.34
     Orig
    -1.33
     Retrieved
    -1.31
     compr
    -1.30
    EVA
    -1.30
    POSITIVE LOGITS
    tailed
    1.53
    rend
    1.42
    strings
    1.34
    sex
    1.33
    nor
    1.33
    cod
    1.32
     termin
    1.27
    roid
    1.25
    bind
    1.23
    ail
    1.23
    Activations Density 0.002%

    No Known Activations