© 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. 14535
    Prev
    Next
    INDEX
    Explanations

    phrases related to age or the concept of being old

    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
    0:0.08
    1:0.04
    2:0.10
    3:0.06
    4:0.05
    5:0.05
    6:0.15
    7:0.06
    8:0.13
    9:0.16
    10:0.03
    11:0.05
    Negative Logits
     cigarettes
    -3.65
     Sears
    -3.51
    BD
    -3.50
     extingu
    -3.49
    ~~
    -3.48
     dolls
    -3.47
    axter
    -3.44
    Roberts
    -3.43
    ighters
    -3.32
     Roberts
    -3.29
    POSITIVE LOGITS
     Gian
    9.95
     Gi
    4.55
     Michele
    4.32
     Sloven
    4.32
     Giul
    4.29
    Gi
    4.21
     Giovanni
    4.14
     Gingrich
    4.04
     Rove
    4.03
     Sicily
    4.00
    Activations Density 0.000%

    No Known Activations