© 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. 12565
    Prev
    Next
    INDEX
    Explanations

    occurrences of the substring "n" and variations of the word "journal."

    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
    0:0.04
    1:0.04
    2:0.04
    3:0.09
    4:0.02
    5:0.03
    6:0.12
    7:0.04
    8:0.03
    9:0.43
    10:0.03
    11:0.04
    Negative Logits
     Dunham
    -4.62
    uga
    -3.67
    Dun
    -3.56
    oğ
    -3.44
     pear
    -3.27
     dur
    -3.27
    EGIN
    -3.24
    GD
    -3.18
     ga
    -3.13
     Xue
    -3.11
    POSITIVE LOGITS
    ist
    5.40
    IST
    5.18
    ists
    5.12
    rist
    4.89
    iste
    4.64
    ism
    4.50
    ISM
    4.15
    ista
    4.04
     Manz
    4.00
    ismo
    3.97
    Activations Density 0.006%

    No Known Activations