© 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. 2-ATT-KK
    11. 13389
    Prev
    Next
    INDEX
    Explanations

    names of locations and companies

    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
    0:0.05
    1:0.05
    2:0.14
    3:0.14
    4:0.03
    5:0.15
    6:0.03
    7:0.03
    8:0.05
    9:0.17
    10:0.08
    11:0.03
    Negative Logits
    PDATE
    -1.77
    theless
    -1.63
     guesses
    -1.59
     payoff
    -1.49
     repet
    -1.46
     acknow
    -1.45
     fortun
    -1.43
     grat
    -1.42
     guessed
    -1.40
     typed
    -1.39
    POSITIVE LOGITS
    tyard
    1.73
    iasco
    1.60
     Trail
    1.56
    undrum
    1.54
    istries
    1.50
    owder
    1.48
    aird
    1.47
    ndum
    1.47
    utra
    1.47
    atorium
    1.47
    Activations Density 0.648%

    No Known Activations