© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 8666
    Prev
    Next
    INDEX
    Explanations

    references to locations or significant geographical features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.04
    2:0.13
    3:0.19
    4:0.03
    5:0.04
    6:0.07
    7:0.13
    8:0.15
    9:0.04
    10:0.06
    11:0.03
    Negative Logits
     fide
    -1.25
     behold
    -1.21
     hump
    -1.09
     Honduras
    -1.09
    vironment
    -1.08
     scrimmage
    -1.07
     perjury
    -1.07
    gow
    -1.06
    glers
    -1.06
     landslide
    -1.03
    POSITIVE LOGITS
    igraph
    1.20
     Nightmares
    1.06
     Night
    1.04
    erb
    1.04
     Haunted
    1.03
     Corner
    1.02
    anz
    1.01
     Zoro
    1.01
     Bits
    0.99
     Guide
    0.99
    Activations Density 0.057%

    No Known Activations