© 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. 45108
    Prev
    Next
    INDEX
    Explanations

    statements reflecting beliefs or opinions, particularly in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.02
    1:0.02
    2:0.36
    3:0.17
    4:0.08
    5:0.04
    6:0.03
    7:0.04
    8:0.04
    9:0.05
    10:0.05
    11:0.05
    Negative Logits
    eton
    -1.70
     Mash
    -1.67
    sembly
    -1.63
    assad
    -1.62
    inburgh
    -1.60
    utic
    -1.57
    lez
    -1.51
    bilt
    -1.51
    xit
    -1.51
    作
    -1.49
    POSITIVE LOGITS
     wont
    1.59
     sucked
    1.56
     ain
    1.56
     mysteriously
    1.53
     insufficient
    1.52
     cones
    1.50
     nowhere
    1.47
     flooded
    1.47
    nt
    1.45
     rightfully
    1.44
    Activations Density 0.099%

    No Known Activations