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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22697
    Prev
    Next
    INDEX
    Explanations

    information related to emergency medical situations and actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases indicating emergency responses or actions taken in urgent situations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.05
    1:0.02
    2:0.12
    3:0.05
    4:0.25
    5:0.03
    6:0.03
    7:0.02
    8:0.20
    9:0.10
    10:0.05
    11:0.02
    Negative Logits
    jiang
    -1.43
    FORE
    -1.36
     ¶
    -1.27
     Tribe
    -1.22
    GF
    -1.22
    %:
    -1.19
    TD
    -1.19
     Sins
    -1.18
     Ninth
    -1.16
     Practices
    -1.15
    POSITIVE LOGITS
    livion
    1.50
     jog
    1.48
     curtains
    1.42
     vomit
    1.38
     orgasm
    1.37
     volley
    1.35
     flames
    1.35
     gunfire
    1.32
     showc
    1.32
     dusk
    1.30
    Activations Density 0.004%

    No Known Activations