© 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. 10383
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to actions and decision-making processes

    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
    0:0.03
    1:0.04
    2:0.03
    3:0.03
    4:0.10
    5:0.03
    6:0.09
    7:0.41
    8:0.02
    9:0.03
    10:0.03
    11:0.12
    Negative Logits
    assault
    -2.79
     Enforcement
    -2.66
     ##
    -2.55
    edged
    -2.52
    Strike
    -2.49
     Assault
    -2.47
     Slaughter
    -2.35
     Charge
    -2.34
    Gar
    -2.30
    demand
    -2.27
    POSITIVE LOGITS
     McD
    3.03
     Norwich
    2.87
     Nokia
    2.86
     Twins
    2.81
    GBT
    2.81
     Celt
    2.73
     PNG
    2.62
    ajor
    2.61
    woods
    2.60
    ochond
    2.56
    Activations Density 0.015%

    No Known Activations