© 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. 9-ATT-KK
    11. 7533
    Prev
    Next
    INDEX
    Explanations

    updates and announcements related to software releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.17
    1:0.02
    2:0.28
    3:0.09
    4:0.05
    5:0.09
    6:0.03
    7:0.08
    8:0.06
    9:0.03
    10:0.04
    11:0.01
    Negative Logits
     Berm
    -2.42
     Fou
    -2.41
     narciss
    -2.35
     fallacy
    -2.35
     hyster
    -2.32
     foul
    -2.29
     psychic
    -2.26
     prostitution
    -2.24
     motel
    -2.24
     Freud
    -2.22
    POSITIVE LOGITS
     update
    4.71
     Updates
    4.25
     updates
    4.24
     Update
    4.14
     upgrade
    4.06
    Version
    3.97
     patches
    3.89
     updated
    3.88
     upgrades
    3.81
     upgraded
    3.77
    Activations Density 0.679%

    No Known Activations