© 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. 16379
    Prev
    Next
    INDEX
    Explanations

    logical connections and contrasts within statements

    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
    1:0.01
    2:0.07
    3:0.04
    4:0.06
    5:0.03
    6:0.23
    7:0.04
    8:0.06
    9:0.27
    10:0.02
    11:0.04
    Negative Logits
     Klu
    -3.73
    FB
    -3.70
    bane
    -3.65
    Nap
    -3.48
    oth
    -3.38
    wu
    -3.38
     Schw
    -3.30
     Clemson
    -3.29
     crochet
    -3.28
    otle
    -3.27
    POSITIVE LOGITS
     Mir
    10.46
    Mir
    9.78
    mir
    8.00
     mir
    7.14
     Mirage
    6.26
     Mirror
    5.81
     Miranda
    5.47
     mirrors
    4.84
     mirror
    4.64
     Marsh
    4.44
    Activations Density 0.005%

    No Known Activations