© 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. 17851
    Prev
    Next
    INDEX
    Explanations

    direct quotes and statements made by individuals

    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
    0:0.03
    1:0.09
    2:0.07
    3:0.10
    4:0.09
    5:0.17
    6:0.05
    7:0.17
    8:0.07
    9:0.04
    10:0.05
    11:0.02
    Negative Logits
    arist
    -2.56
    kefeller
    -2.49
    BuyableInstoreAndOnline
    -2.27
    adish
    -2.20
    oglu
    -2.19
    ć
    -2.12
    alia
    -2.11
    arest
    -2.11
    byn
    -2.08
     astroph
    -2.05
    POSITIVE LOGITS
    He
    2.48
     newsp
    2.34
     he
    2.33
     his
    2.26
     himself
    2.25
     He
    2.23
    his
    2.10
    he
    2.08
     Origin
    1.91
     preliminary
    1.86
    Activations Density 0.190%

    No Known Activations