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. 3-ATT-KK
    6. 10219
    Prev
    Next
    INDEX
    Explanations

    terms related to injuries and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.05
    2:0.08
    3:0.05
    4:0.05
    5:0.06
    6:0.06
    7:0.07
    8:0.13
    9:0.20
    10:0.08
    11:0.08
    Negative Logits
    Iss
    -1.35
     adop
    -1.26
    leground
    -1.22
    udget
    -1.20
    Policy
    -1.18
     evolves
    -1.17
    soDeliveryDate
    -1.17
    Ob
    -1.16
    Aren
    -1.15
     optim
    -1.14
    POSITIVE LOGITS
     █
    1.25
    blance
    1.24
    qus
    1.22
     penetrating
    1.17
    rapnel
    1.16
    severe
    1.14
     accomp
    1.12
     gunshot
    1.11
     wounding
    1.11
    tu
    1.11
    Activations Density 0.010%

    No Known Activations