© 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. 10-ATT-KK
    11. 21846
    Prev
    Next
    INDEX
    Explanations

    terms related to data or information management and corporate interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.08
    2:0.06
    3:0.05
    4:0.08
    5:0.04
    6:0.25
    7:0.16
    8:0.04
    9:0.06
    10:0.03
    11:0.05
    Negative Logits
     Rule
    -2.86
     Clip
    -2.67
     departures
    -2.66
     Appeals
    -2.53
     actionGroup
    -2.52
     nominations
    -2.42
    Rule
    -2.40
     Seat
    -2.39
    Tre
    -2.28
    engers
    -2.26
    POSITIVE LOGITS
     provide
    3.51
    prov
    3.47
     providing
    3.33
     Provide
    3.19
     provided
    3.18
     provides
    3.17
     provider
    3.07
     subcontract
    2.99
     volunt
    2.97
     supplied
    2.92
    Activations Density 0.026%

    No Known Activations