Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 7659
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their connections or roles within a particular narrative or context

    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
    1:0.02
    2:0.06
    3:0.06
    4:0.04
    5:0.04
    6:0.34
    7:0.04
    8:0.07
    9:0.14
    10:0.04
    11:0.03
    Negative Logits
     OPT
    -3.79
    �
    -3.35
     NR
    -3.34
     biod
    -3.32
    Thom
    -3.31
     Delta
    -3.31
     Rih
    -3.30
     cleans
    -3.29
     distribut
    -3.24
     mammals
    -3.23
    POSITIVE LOGITS
     Castle
    10.38
     castle
    8.72
     castles
    8.18
    castle
    6.38
    Cast
    5.60
    iege
    4.82
     fortress
    4.80
     Abbey
    4.74
     Knight
    4.22
     Fortress
    4.19
    Activations Density 0.004%

    No Known Activations