© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 18333
    Prev
    Next
    INDEX
    Explanations

    instances of the character "á" in various contexts or patterns

    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
    1:0.06
    2:0.04
    3:0.10
    4:0.03
    5:0.06
    6:0.11
    7:0.04
    8:0.04
    9:0.33
    10:0.03
    11:0.05
    Negative Logits
     Sear
    -3.46
    hunt
    -3.33
     Rove
    -3.25
    oster
    -3.20
    ilan
    -3.11
    inis
    -3.09
     Dian
    -3.07
    oin
    -3.00
    oa
    -2.98
     RL
    -2.98
    POSITIVE LOGITS
    �
    5.27
    �
    4.52
     Symb
    3.86
     Matthews
    3.58
     Mub
    3.32
     Micha
    3.30
     metre
    3.29
    Mich
    3.15
    cycl
    3.15
     transm
    3.06
    Activations Density 0.001%

    No Known Activations