© 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. 11086
    Prev
    Next
    INDEX
    Explanations

    statements about choices and options regarding serious decisions or situations

    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
    0:0.04
    1:0.03
    2:0.08
    3:0.15
    4:0.04
    5:0.10
    6:0.02
    7:0.10
    8:0.03
    9:0.02
    10:0.30
    11:0.02
    Negative Logits
     properly
    -2.40
     harmon
    -2.16
     coincided
    -2.14
     anecd
    -2.01
     supra
    -2.01
     underestimated
    -1.99
    enos
    -1.99
    ancies
    -1.98
    eworthy
    -1.98
     synthes
    -1.92
    POSITIVE LOGITS
    Either
    4.55
     Either
    4.21
    either
    3.53
    Option
    3.45
     either
    3.26
    ichever
    3.03
    Choice
    3.02
     whichever
    2.95
    Choose
    2.85
     Options
    2.85
    Activations Density 0.129%

    No Known Activations