© 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. 2-ATT-KK
    11. 22616
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    names of people or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.04
    2:0.21
    3:0.06
    4:0.12
    5:0.10
    6:0.03
    7:0.03
    8:0.05
    9:0.18
    10:0.05
    11:0.03
    Negative Logits
     skelet
    -1.63
     brig
    -1.36
     smoked
    -1.35
    cooked
    -1.23
     Rove
    -1.23
     psychiat
    -1.19
     steroid
    -1.16
     gamb
    -1.16
     rehabilit
    -1.15
     dynam
    -1.14
    POSITIVE LOGITS
    fecture
    1.70
    riks
    1.60
    boa
    1.51
    kai
    1.49
    ensis
    1.45
    anca
    1.43
    vu
    1.42
    ère
    1.39
    �
    1.36
    arta
    1.36
    Activations Density 0.002%

    No Known Activations