© 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. 27745
    Prev
    Next
    INDEX
    Explanations

    terms related to financial metrics and taxation

    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
    0:0.02
    1:0.04
    2:0.08
    3:0.04
    4:0.03
    5:0.04
    6:0.45
    7:0.07
    8:0.03
    9:0.04
    10:0.06
    11:0.04
    Negative Logits
    ashtra
    -1.71
     Wonderland
    -1.66
    trump
    -1.42
    MAC
    -1.38
    Gate
    -1.34
    ��
    -1.28
    nai
    -1.27
     Lumpur
    -1.24
    AFTA
    -1.23
     Dove
    -1.23
    POSITIVE LOGITS
    iferation
    1.55
    phasis
    1.50
    ciation
    1.49
    charging
    1.48
    ittance
    1.47
    funding
    1.47
    earance
    1.42
    charge
    1.38
    iciency
    1.36
    uments
    1.31
    Activations Density 0.007%

    No Known Activations