© 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. 18351
    Prev
    Next
    INDEX
    Explanations

    the opening parenthesis

    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
    0:0.07
    1:0.03
    2:0.08
    3:0.05
    4:0.07
    5:0.06
    6:0.16
    7:0.04
    8:0.05
    9:0.26
    10:0.03
    11:0.05
    Negative Logits
    Psy
    -3.10
     Psychology
    -3.10
     Planetary
    -3.08
     Cognitive
    -2.96
     robotic
    -2.92
     artificial
    -2.89
     Maintenance
    -2.88
     Vanguard
    -2.85
     Awareness
    -2.74
     maintenance
    -2.71
    POSITIVE LOGITS
     Rouhani
    3.58
    lam
    3.36
    eli
    3.12
     Zhang
    3.10
    li
    3.04
     Modi
    3.02
     Chow
    2.98
     Lud
    2.97
    iq
    2.95
     Cuomo
    2.92
    Activations Density 0.000%

    No Known Activations