© 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. 2260
    Prev
    Next
    INDEX
    Explanations

    references to technological products and their features

    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
    0:0.10
    1:0.06
    2:0.06
    3:0.09
    4:0.16
    5:0.11
    6:0.11
    7:0.04
    8:0.06
    9:0.08
    10:0.02
    11:0.06
    Negative Logits
    accompan
    -2.40
     uncond
    -2.26
    Asset
    -2.22
     conduc
    -2.20
     submar
    -2.16
    Weapons
    -2.16
     arsen
    -2.10
     colonel
    -2.09
    estern
    -2.09
    ento
    -2.06
    POSITIVE LOGITS
     Yi
    2.53
     GS
    2.44
     Mic
    2.44
     Kik
    2.42
     Snapdragon
    2.41
     Quartz
    2.36
     Teg
    2.35
     Pioneer
    2.33
     Pixel
    2.31
     512
    2.31
    Activations Density 0.114%

    No Known Activations