© 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. 19607
    Prev
    Next
    INDEX
    Explanations

    hashtags and numerical values

    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
    1:0.03
    2:0.02
    3:0.05
    4:0.03
    5:0.05
    6:0.34
    7:0.04
    8:0.05
    9:0.18
    10:0.04
    11:0.06
    Negative Logits
     Chimera
    -4.06
     bom
    -3.76
     comb
    -3.67
    Alice
    -3.60
     Catalyst
    -3.54
    ortmund
    -3.53
     Cliff
    -3.52
     Barber
    -3.48
    ヴァ
    -3.42
    ouver
    -3.37
    POSITIVE LOGITS
     SD
    9.50
    SD
    7.95
    sd
    6.48
     sd
    6.09
     SDL
    4.76
     Samp
    4.50
    Charg
    4.05
     Sund
    4.00
     Sinn
    3.97
     SDK
    3.80
    Activations Density 0.002%

    No Known Activations