© 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. 3384
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical data and references to quantities

    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
    1:0.04
    2:0.29
    3:0.06
    4:0.14
    5:0.03
    6:0.05
    7:0.11
    8:0.04
    9:0.05
    10:0.05
    11:0.05
    Negative Logits
    Lago
    -1.94
    swer
    -1.93
    aturday
    -1.81
    cknow
    -1.74
    lished
    -1.71
    ruary
    -1.67
    orum
    -1.63
    �士
    -1.62
     Journalists
    -1.60
    rity
    -1.55
    POSITIVE LOGITS
     endemic
    1.63
     palpable
    1.61
     prevalent
    1.59
     tantal
    1.58
     stickers
    1.55
     ILCS
    1.52
    abi
    1.52
    qi
    1.50
    untled
    1.48
     bombshell
    1.47
    Activations Density 0.001%

    No Known Activations