© 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. 15579
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential or conditional scenarios

    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
    0:0.05
    1:0.02
    2:0.05
    3:0.17
    4:0.01
    5:0.06
    6:0.01
    7:0.04
    8:0.02
    9:0.01
    10:0.49
    11:0.02
    Negative Logits
    main
    -2.13
    commit
    -2.02
    OOOOOOOO
    -1.99
     equals
    -1.84
    establishment
    -1.81
     cohesive
    -1.81
    finals
    -1.81
     constitu
    -1.77
    ilib
    -1.75
     meticulously
    -1.73
    POSITIVE LOGITS
     someday
    3.01
     inadvertently
    2.73
     sooner
    2.68
     mistaken
    2.60
     momentarily
    2.41
     Alternatively
    2.40
     alternatively
    2.32
     misinterpret
    2.32
     unwittingly
    2.31
     differently
    2.30
    Activations Density 0.639%

    No Known Activations