© 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. 10838
    Prev
    Next
    INDEX
    Explanations

    statements or phrases that express personal feelings and experiences related to decision-making or reflection

    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
    0:0.06
    1:0.02
    2:0.07
    3:0.15
    4:0.03
    5:0.06
    6:0.02
    7:0.05
    8:0.02
    9:0.02
    10:0.43
    11:0.02
    Negative Logits
    rehensive
    -2.10
    cern
    -2.04
    uggest
    -2.03
    rief
    -1.97
    estic
    -1.96
    ounces
    -1.96
    YN
    -1.93
    obbies
    -1.89
    oller
    -1.88
    ATT
    -1.88
    POSITIVE LOGITS
     deserved
    3.00
     lucky
    2.95
     deserving
    2.81
     deserve
    2.77
     better
    2.56
     correctly
    2.50
     ripe
    2.48
     perfect
    2.44
     advant
    2.43
     entit
    2.41
    Activations Density 0.255%

    No Known Activations