© 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. 18490
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a downward movement or decline

    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
    0:0.07
    1:0.07
    2:0.07
    3:0.08
    4:0.09
    5:0.08
    6:0.09
    7:0.07
    8:0.07
    9:0.07
    10:0.09
    11:0.08
    Negative Logits
    \":
    -2.30
     ---
    -2.28
     Ambro
    -2.26
     legendary
    -2.23
     Faust
    -2.19
     Shea
    -2.11
     antim
    -2.06
     Marino
    -2.06
    mb
    -2.05
     art
    -2.03
    POSITIVE LOGITS
    ��
    2.46
     Nanto
    2.44
    elling
    2.37
    Storage
    2.34
     Summer
    2.33
    龍契士
    2.32
     pupils
    2.30
    emouth
    2.29
    ulus
    2.28
    incial
    2.24
    Activations Density 0.000%

    No Known Activations