© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 3415
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal choice and agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.08
    3:0.07
    4:0.40
    5:0.03
    6:0.04
    7:0.14
    8:0.02
    9:0.03
    10:0.04
    11:0.03
    Negative Logits
     Purg
    -1.77
    uably
    -1.68
    untarily
    -1.56
    artifacts
    -1.55
     fug
    -1.50
     suburb
    -1.45
    lost
    -1.43
    fried
    -1.43
    iform
    -1.42
    oward
    -1.42
    POSITIVE LOGITS
    ographers
    2.24
     discretion
    1.85
     whoever
    1.83
     admins
    1.81
     producers
    1.76
    erity
    1.75
     Profession
    1.73
     stakeholders
    1.70
     volunteers
    1.70
     collaborators
    1.68
    Activations Density 0.011%

    No Known Activations