© 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. 10-ATT-KK
    11. 21107
    Prev
    Next
    INDEX
    Explanations

    financial transactions related to investments or expenditures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.19
    2:0.06
    3:0.04
    4:0.03
    5:0.02
    6:0.14
    7:0.05
    8:0.02
    9:0.05
    10:0.19
    11:0.04
    Negative Logits
    backer
    -3.00
    Reloaded
    -2.90
    illa
    -2.82
     shield
    -2.81
    GD
    -2.80
    ilan
    -2.72
     AH
    -2.69
    illas
    -2.68
     salads
    -2.63
     Klu
    -2.63
    POSITIVE LOGITS
     Nob
    9.84
    Nob
    9.11
    nob
    5.82
     Noble
    5.41
    Nich
    4.07
     Nich
    3.94
     Nim
    3.93
     nob
    3.83
     MacArthur
    3.70
     Hiro
    3.66
    Activations Density 0.000%

    No Known Activations