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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11269
    Prev
    Next
    INDEX
    Explanations

    patterns of repeated words or phrases within the text

    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
    0:0.16
    1:0.06
    2:0.03
    3:0.05
    4:0.05
    5:0.04
    6:0.11
    7:0.03
    8:0.03
    9:0.31
    10:0.03
    11:0.05
    Negative Logits
     Minotaur
    -3.95
     Memphis
    -3.64
    ronics
    -3.48
    ebus
    -3.48
     Pine
    -3.44
    phis
    -3.26
     Hades
    -3.23
     Charm
    -3.22
    obos
    -3.21
     Cutler
    -3.20
    POSITIVE LOGITS
     article
    5.66
     Article
    5.66
     articles
    5.64
     Articles
    5.42
    article
    5.15
    articles
    4.86
    Article
    4.25
     ARTICLE
    3.92
     encyclopedia
    3.55
     magazines
    3.42
    Activations Density 0.010%

    No Known Activations