© 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. 5-ATT-KK
    11. 34079
    Prev
    Next
    INDEX
    Explanations

    specific phrases and elements that hint at physical transformations or movements

    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
    1:0.03
    2:0.06
    3:0.06
    4:0.13
    5:0.04
    6:0.07
    7:0.31
    8:0.03
    9:0.04
    10:0.08
    11:0.07
    Negative Logits
    ertation
    -1.77
    CVE
    -1.69
    anza
    -1.63
    monary
    -1.56
    phies
    -1.56
    forts
    -1.54
    NetMessage
    -1.53
    ailability
    -1.50
    secret
    -1.48
    borgh
    -1.46
    POSITIVE LOGITS
     alternating
    2.15
     inverted
    1.92
     upright
    1.89
     clock
    1.86
     axis
    1.83
     aligned
    1.82
     rotating
    1.78
     tilted
    1.78
     hither
    1.75
     rotated
    1.75
    Activations Density 0.002%

    No Known Activations