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. 7642
    Prev
    Next
    INDEX
    Explanations

    technical terms and safety warnings regarding vaping devices and their usage

    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
    0:0.19
    1:0.03
    2:0.14
    3:0.09
    4:0.04
    5:0.07
    6:0.09
    7:0.04
    8:0.10
    9:0.08
    10:0.03
    11:0.04
    Negative Logits
     Sharif
    -3.30
     Karachi
    -3.25
     Jinn
    -3.10
     Belichick
    -3.02
     archae
    -3.01
     archaeologists
    -2.90
    ichick
    -2.90
     UNESCO
    -2.88
     cardinal
    -2.86
     Desmond
    -2.85
    POSITIVE LOGITS
     vape
    7.04
     vaping
    6.69
     Vapor
    5.71
     vapor
    5.56
     Nicotine
    5.56
     nicotine
    5.40
     VG
    5.36
     vap
    5.02
     juices
    4.79
     juice
    4.63
    Activations Density 0.004%

    No Known Activations