© 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. 5-ATT-KK
    11. 34049
    Prev
    Next
    INDEX
    Explanations

    conjunctions and conditional phrases that suggest addition or continuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.02
    2:0.05
    3:0.08
    4:0.08
    5:0.02
    6:0.43
    7:0.08
    8:0.03
    9:0.04
    10:0.05
    11:0.05
    Negative Logits
     precaution
    -1.56
     Samurai
    -1.22
    atform
    -1.19
     Kik
    -1.16
     Ruk
    -1.13
     Indust
    -1.12
     Miz
    -1.11
     Respons
    -1.11
     mats
    -1.08
     hostage
    -1.08
    POSITIVE LOGITS
    rouse
    1.75
    ycle
    1.41
    aple
    1.37
    ulhu
    1.34
    uce
    1.34
    atche
    1.33
    ivably
    1.32
    idate
    1.32
    unte
    1.32
    lege
    1.31
    Activations Density 0.158%

    No Known Activations