© 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. 21208
    Prev
    Next
    INDEX
    Explanations

    initials or single letters followed by significant actions or descriptors

    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
    0:0.05
    1:0.05
    2:0.04
    3:0.12
    4:0.04
    5:0.05
    6:0.12
    7:0.04
    8:0.05
    9:0.29
    10:0.04
    11:0.03
    Negative Logits
    Activ
    -3.13
     Mara
    -2.99
    resp
    -2.88
    iasis
    -2.86
    asma
    -2.78
     AAC
    -2.77
     ACS
    -2.76
    aband
    -2.75
    sr
    -2.75
     guiActiveUnfocused
    -2.74
    POSITIVE LOGITS
     Dug
    3.06
     eleph
    2.87
     Bram
    2.68
     Buch
    2.63
    Wonder
    2.56
     rooting
    2.56
     ARTICLE
    2.56
     Pound
    2.52
     Colin
    2.49
     mathemat
    2.49
    Activations Density 0.001%

    No Known Activations