© 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. 9-ATT-KK
    11. 10116
    Prev
    Next
    INDEX
    Explanations

    instances of names, titles, or phrases that emphasize cultural references or commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.02
    2:0.04
    3:0.53
    4:0.03
    5:0.05
    6:0.02
    7:0.06
    8:0.04
    9:0.02
    10:0.06
    11:0.04
    Negative Logits
    byn
    -1.82
    tein
    -1.72
    bots
    -1.58
     squat
    -1.56
     planner
    -1.55
     workshops
    -1.55
    xit
    -1.53
    yip
    -1.51
    ynt
    -1.51
    CHO
    -1.51
    POSITIVE LOGITS
    dot
    1.52
    license
    1.50
    \.
    1.36
    Date
    1.34
    �
    1.28
     fortunately
    1.28
    beam
    1.28
    ilogy
    1.28
    ש
    1.26
    Repeat
    1.24
    Activations Density 1.235%

    No Known Activations