© 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. 22788
    Prev
    Next
    INDEX
    Explanations

    phrases related to serious events or tragedies

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

    emotions and expressions of loss or difficulty

    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
    0:0.07
    1:0.02
    2:0.09
    3:0.16
    4:0.18
    5:0.07
    6:0.03
    7:0.02
    8:0.07
    9:0.16
    10:0.06
    11:0.03
    Negative Logits
    ouston
    -1.21
     carbohyd
    -1.21
    aughtered
    -1.20
    arro
    -1.17
     drums
    -1.16
     Bullets
    -1.16
    leased
    -1.16
    waukee
    -1.15
    uilt
    -1.14
     pian
    -1.13
    POSITIVE LOGITS
     imaginable
    2.22
    ever
    1.59
     ever
    1.59
     EVER
    1.57
    Ever
    1.54
     achievable
    1.45
     possible
    1.44
     practicable
    1.38
     conceivable
    1.34
     Ever
    1.33
    Activations Density 0.006%

    No Known Activations