© 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. 2082
    Prev
    Next
    INDEX
    Explanations

    references to notable locations and landmarks

    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
    0:0.11
    1:0.02
    2:0.20
    3:0.16
    4:0.08
    5:0.09
    6:0.04
    7:0.06
    8:0.07
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
    Serial
    -2.42
    imony
    -2.29
    illus
    -2.27
    avior
    -2.25
     parity
    -2.25
     retracted
    -2.25
     actu
    -2.24
     replication
    -2.23
    isner
    -2.20
     subsystem
    -2.19
    POSITIVE LOGITS
     tourist
    4.11
     Tours
    3.83
     tourists
    3.66
     stroll
    3.59
     beaches
    3.56
     scenic
    3.50
     Tourism
    3.48
     Visitors
    3.42
     tourism
    3.42
     attractions
    3.41
    Activations Density 0.582%

    No Known Activations