© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7618
    Prev
    Next
    INDEX
    Explanations

    financial figures and measurements, especially in the context of sports or market analysis

    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
    0:0.16
    1:0.18
    2:0.08
    3:0.04
    4:0.04
    5:0.17
    6:0.05
    7:0.02
    8:0.07
    9:0.06
    10:0.04
    11:0.03
    Negative Logits
     Ther
    -2.34
     Man
    -2.17
     Chau
    -2.14
     Ce
    -2.11
     Hale
    -2.10
     Grac
    -2.10
     Lear
    -2.06
     Tel
    -2.05
     Haram
    -1.98
     Lan
    -1.95
    POSITIVE LOGITS
    percent
    2.44
    %]
    2.41
    asses
    2.27
    number
    2.17
    ム
    2.16
    覚醒
    2.15
    ickets
    2.13
    pees
    2.12
    asons
    2.12
    ithing
    2.11
    Activations Density 0.001%

    No Known Activations