© 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. 43458
    Prev
    Next
    INDEX
    Explanations

    currency values and financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.07
    1:0.03
    2:0.12
    3:0.06
    4:0.05
    5:0.04
    6:0.31
    7:0.03
    8:0.05
    9:0.05
    10:0.06
    11:0.08
    Negative Logits
    \/\/
    -1.47
    itiveness
    -1.38
    undown
    -1.37
    natureconservancy
    -1.34
    urus
    -1.23
    Reviewer
    -1.22
     IMAGES
    -1.22
    Contents
    -1.21
    =-=-=-=-
    -1.20
     Femin
    -1.19
    POSITIVE LOGITS
     apiece
    1.55
     pounds
    1.35
    dc
    1.31
     equivalents
    1.31
    iah
    1.20
     respectively
    1.19
    aud
    1.18
    lbs
    1.16
     Ct
    1.16
     lbs
    1.15
    Activations Density 0.038%

    No Known Activations