© 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. 2427
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize connections, implications, or contrasts in ideas

    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
    1:0.11
    2:0.10
    3:0.12
    4:0.06
    5:0.05
    6:0.02
    7:0.11
    8:0.05
    9:0.02
    10:0.13
    11:0.06
    Negative Logits
    Setup
    -2.64
    entary
    -2.61
    apter
    -2.61
    herical
    -2.58
    enne
    -2.55
    ttp
    -2.52
    mins
    -2.49
    prisingly
    -2.48
    Db
    -2.46
    iatus
    -2.45
    POSITIVE LOGITS
     criticizing
    3.50
     condemning
    3.48
     denouncing
    3.41
     undermining
    3.19
     alleging
    3.13
     blaming
    3.13
     dispar
    3.08
     defund
    3.05
     praising
    3.04
     criticized
    3.02
    Activations Density 0.094%

    No Known Activations