© 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. 2-ATT-KK
    11. 14965
    Prev
    Next
    INDEX
    Explanations

    statements or descriptions involving riding or being on bikes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.03
    2:0.15
    3:0.06
    4:0.15
    5:0.05
    6:0.02
    7:0.02
    8:0.19
    9:0.13
    10:0.05
    11:0.02
    Negative Logits
    zsche
    -1.76
    rences
    -1.32
    matical
    -1.27
     Seller
    -1.25
    mberg
    -1.23
     Lich
    -1.19
     Kinnikuman
    -1.18
    gemony
    -1.15
    angible
    -1.14
    nces
    -1.13
    POSITIVE LOGITS
     wheels
    1.61
     stairs
    1.52
     heels
    1.52
     wedge
    1.41
     wagon
    1.41
     wheelchair
    1.35
     tails
    1.33
     opposite
    1.32
    ousel
    1.28
     elevator
    1.24
    Activations Density 0.007%

    No Known Activations