© 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. 1965
    Prev
    Next
    INDEX
    Explanations

    names of individuals or characters in the text

    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
    0:0.06
    1:0.25
    2:0.02
    3:0.03
    4:0.03
    5:0.33
    6:0.03
    7:0.01
    8:0.04
    9:0.06
    10:0.05
    11:0.03
    Negative Logits
     Companies
    -1.90
     Newsp
    -1.86
     Colleges
    -1.83
     boxes
    -1.83
     Publishers
    -1.81
     Outdoor
    -1.81
     Worldwide
    -1.80
     arrows
    -1.72
     associations
    -1.71
     divest
    -1.71
    POSITIVE LOGITS
    amin
    2.48
    escription
    2.28
    amina
    2.22
     Nico
    2.22
     Gabriel
    2.20
    irit
    2.19
    ry
    2.13
     Seym
    2.12
    Jenn
    2.09
     Seb
    2.07
    Activations Density 0.032%

    No Known Activations