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. 2-ATT-KK
    6. 13969
    Prev
    Next
    INDEX
    Explanations

    sentences related to healthcare and medical care

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.04
    2:0.19
    3:0.06
    4:0.08
    5:0.09
    6:0.03
    7:0.03
    8:0.08
    9:0.21
    10:0.05
    11:0.03
    Negative Logits
    etheus
    -1.73
     sidx
    -1.59
    bable
    -1.50
    clair
    -1.46
    ppel
    -1.38
    ieg
    -1.38
    selage
    -1.36
    ena
    -1.35
    天
    -1.35
    vez
    -1.35
    POSITIVE LOGITS
     impaired
    1.33
     Scientology
    1.25
     bere
    1.23
     PG
    1.22
     childbirth
    1.21
     Mechdragon
    1.20
     prevention
    1.19
     Samar
    1.17
     Clinic
    1.14
     Doctors
    1.14
    Activations Density 0.031%

    No Known Activations