© 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. 4297
    Prev
    Next
    INDEX
    Explanations

    calls to action related to subscribing or signing up for newsletters

    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
    0:0.18
    1:0.02
    2:0.09
    3:0.07
    4:0.06
    5:0.13
    6:0.06
    7:0.07
    8:0.12
    9:0.01
    10:0.12
    11:0.02
    Negative Logits
    frames
    -2.13
     Kubrick
    -2.06
     Kenn
    -2.00
    ucket
    -1.99
     Uniform
    -1.99
     mapping
    -1.99
    Rat
    -1.97
     artificially
    -1.94
     fond
    -1.90
    =~
    -1.90
    POSITIVE LOGITS
    lehem
    2.27
     kickoff
    2.24
     Yose
    2.19
    morning
    2.16
     keynote
    2.12
     Bethlehem
    2.10
    DH
    2.05
    steen
    2.03
    ecast
    2.02
    oba
    1.99
    Activations Density 0.003%

    No Known Activations