© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10007
    Prev
    Next
    INDEX
    Explanations

    specific instances of significant events related to healthcare

    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
    0:0.04
    1:0.01
    2:0.06
    3:0.37
    4:0.04
    5:0.09
    6:0.02
    7:0.11
    8:0.04
    9:0.02
    10:0.09
    11:0.05
    Negative Logits
    ensibly
    -2.38
    Individual
    -2.26
    mittedly
    -2.16
    ustomed
    -2.02
    esides
    -2.02
    rarily
    -2.01
    Footnote
    -1.96
    requently
    -1.93
    approximately
    -1.92
    oubtedly
    -1.90
    POSITIVE LOGITS
     feds
    2.62
     quake
    2.28
     Belfast
    2.26
     meltdown
    2.08
     pope
    2.08
     playbook
    2.06
     Replay
    2.03
     handshake
    1.99
     takeover
    1.95
     blame
    1.93
    Activations Density 0.995%

    No Known Activations