© 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. 9-ATT-KK
    11. 8138
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal perspectives and beliefs

    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
    0:0.03
    1:0.44
    2:0.05
    3:0.06
    4:0.05
    5:0.04
    6:0.05
    7:0.06
    8:0.02
    9:0.07
    10:0.07
    11:0.03
    Negative Logits
     ninth
    -3.64
     tenth
    -3.43
     Seventh
    -3.25
     seventh
    -3.15
     Fifth
    -3.15
     eighth
    -3.00
    fourth
    -2.93
     sixth
    -2.90
    fifth
    -2.81
    iba
    -2.76
    POSITIVE LOGITS
     can
    5.03
    can
    4.56
    Can
    4.35
     Can
    4.23
     CAN
    3.85
    CAN
    3.43
     able
    3.19
     cant
    2.56
    ca
    2.52
     Canad
    2.52
    Activations Density 0.081%

    No Known Activations