© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 19339
    Prev
    Next
    INDEX
    Explanations

    significant logistical and humanitarian elements related to migration and aid

    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
    0:0.06
    1:0.01
    2:0.08
    3:0.21
    4:0.02
    5:0.11
    6:0.02
    7:0.06
    8:0.03
    9:0.02
    10:0.31
    11:0.02
    Negative Logits
     inconsistency
    -2.05
     inaction
    -2.05
    boxing
    -2.04
     consequences
    -2.01
     confrontation
    -1.97
     posture
    -1.96
    appropriately
    -1.94
    idelity
    -1.92
     standoff
    -1.92
     hesitation
    -1.87
    POSITIVE LOGITS
     onto
    2.57
     goods
    2.28
     into
    2.26
     from
    2.19
     supplies
    2.14
    from
    2.06
     shipments
    2.05
     looted
    2.04
    rie
    2.03
     medicines
    2.00
    Activations Density 0.177%

    No Known Activations