© 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. 10-ATT-KK
    11. 16642
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a connection to identity and moral dilemmas regarding behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.05
    2:0.05
    3:0.03
    4:0.04
    5:0.06
    6:0.03
    7:0.04
    8:0.50
    9:0.04
    10:0.04
    11:0.04
    Negative Logits
    verning
    -2.37
    formance
    -2.23
    forth
    -2.23
    rer
    -2.21
    pert
    -2.15
    WARD
    -2.14
    ه
    -2.12
    anges
    -2.10
    abouts
    -2.08
    utive
    -2.06
    POSITIVE LOGITS
     or
    9.01
     Or
    7.26
    Or
    7.05
     OR
    6.38
     nor
    5.82
    or
    5.71
     Alternatively
    4.73
     either
    4.33
     Either
    3.99
    Either
    3.98
    Activations Density 0.218%

    No Known Activations