© 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. 5-ATT-KK
    11. 41292
    Prev
    Next
    INDEX
    Explanations

    actions or intentions related to "doing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.17
    3:0.08
    4:0.10
    5:0.05
    6:0.05
    7:0.05
    8:0.30
    9:0.03
    10:0.04
    11:0.03
    Negative Logits
    imil
    -1.63
    dated
    -1.61
    utz
    -1.57
     dwelling
    -1.56
    amaz
    -1.51
     attm
    -1.49
    ptoms
    -1.49
    NetMessage
    -1.46
    voy
    -1.45
     unaccount
    -1.44
    POSITIVE LOGITS
     Pandora
    1.75
    isSpecialOrderable
    1.61
     Alphabet
    1.59
     Mell
    1.58
     Newfoundland
    1.57
     Clinic
    1.57
     fundra
    1.53
     Clancy
    1.49
     Havana
    1.49
     POLITICO
    1.47
    Activations Density 0.012%

    No Known Activations