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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10642
    Prev
    Next
    INDEX
    Explanations

    occurrences of prescription medication discussions and behaviors

    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
    0:0.20
    1:0.03
    2:0.16
    3:0.10
    4:0.03
    5:0.09
    6:0.06
    7:0.06
    8:0.05
    9:0.07
    10:0.05
    11:0.03
    Negative Logits
    aughtered
    -2.74
     incub
    -2.73
     Yoshi
    -2.71
    unity
    -2.64
     shed
    -2.46
    Rust
    -2.45
     organis
    -2.45
     Dirk
    -2.44
     cultured
    -2.43
     Cultural
    -2.38
    POSITIVE LOGITS
     prescriptions
    5.62
     prescription
    5.45
     prescribing
    4.77
     prescribe
    4.42
     pharmacies
    4.38
     pills
    4.35
     medications
    4.16
     medication
    3.94
     pharmacy
    3.82
     presc
    3.57
    Activations Density 0.012%

    No Known Activations