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. 7684
    Prev
    Next
    INDEX
    Explanations

    evidence related to scientific studies and their findings on various topics

    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
    0:0.06
    1:0.01
    2:0.12
    3:0.16
    4:0.04
    5:0.36
    6:0.03
    7:0.04
    8:0.04
    9:0.02
    10:0.04
    11:0.03
    Negative Logits
    ertation
    -3.02
    redit
    -2.96
    displayText
    -2.86
    Document
    -2.81
    tesy
    -2.75
     scient
    -2.74
    MIT
    -2.70
    CLASSIFIED
    -2.64
    Documents
    -2.63
     Investigator
    -2.61
    POSITIVE LOGITS
     wrinkles
    2.52
     effects
    2.50
     gunshot
    2.48
     landsl
    2.42
     alters
    2.42
     aging
    2.41
     rapes
    2.40
     adip
    2.40
     affects
    2.33
     crashes
    2.31
    Activations Density 0.464%

    No Known Activations