© 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. 23131
    Prev
    Next
    INDEX
    Explanations

    pronouns and their associations in various contexts

    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
    1:0.01
    2:0.04
    3:0.12
    4:0.01
    5:0.05
    6:0.02
    7:0.06
    8:0.03
    9:0.02
    10:0.53
    11:0.02
    Negative Logits
     heartbreaking
    -2.63
     invaluable
    -2.18
     tears
    -2.07
     effic
    -2.04
     hardest
    -1.93
     hilarious
    -1.92
     costing
    -1.92
    ateral
    -1.91
     explaining
    -1.89
     cost
    -1.88
    POSITIVE LOGITS
     intends
    2.66
     intention
    2.62
     intend
    2.59
     EVER
    2.58
     hopes
    2.57
     hope
    2.54
     ambitions
    2.45
     presume
    2.40
     aspire
    2.34
     continuation
    2.28
    Activations Density 0.051%

    No Known Activations