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. 5-ATT-KK
    6. 19186
    Prev
    Next
    INDEX
    Explanations

    phrases related to prescription medications and their use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.02
    2:0.06
    3:0.05
    4:0.10
    5:0.03
    6:0.07
    7:0.33
    8:0.04
    9:0.04
    10:0.13
    11:0.07
    Negative Logits
    aucuses
    -2.22
    semble
    -1.66
    ipel
    -1.64
    phabet
    -1.64
    iseum
    -1.53
    moil
    -1.48
    igi
    -1.47
    ftime
    -1.46
    lehem
    -1.45
    Compar
    -1.44
    POSITIVE LOGITS
     dosage
    1.66
     medication
    1.65
     medicines
    1.62
     drugs
    1.61
     medications
    1.61
     vaccines
    1.61
     priced
    1.57
     remedy
    1.57
     vouchers
    1.56
     prescribing
    1.52
    Activations Density 0.004%

    No Known Activations