© 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. 46
    Prev
    Next
    INDEX
    Explanations

    expressions of confusion or disagreement in discussions

    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
    0:0.06
    1:0.02
    2:0.05
    3:0.06
    4:0.04
    5:0.14
    6:0.02
    7:0.02
    8:0.29
    9:0.08
    10:0.11
    11:0.05
    Negative Logits
    gaard
    -1.68
    oos
    -1.59
     anecd
    -1.47
    ghai
    -1.42
    oğ
    -1.39
    Downloadha
    -1.38
    otine
    -1.35
     fishes
    -1.34
    atech
    -1.33
     looph
    -1.31
    POSITIVE LOGITS
    didn
    2.02
    went
    1.91
    Was
    1.82
     thereafter
    1.71
    emed
    1.65
    mostly
    1.61
    Had
    1.60
    did
    1.59
     persisted
    1.56
     lacked
    1.53
    Activations Density 1.018%

    No Known Activations