© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 21930
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to emergency calls and call centers

    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
    0:0.08
    1:0.04
    2:0.14
    3:0.07
    4:0.02
    5:0.12
    6:0.02
    7:0.03
    8:0.09
    9:0.25
    10:0.07
    11:0.03
    Negative Logits
    ahime
    -1.32
     agric
    -1.29
    ebus
    -1.26
    ulz
    -1.24
     qual
    -1.22
     arrang
    -1.20
     seiz
    -1.20
     ornament
    -1.20
     proport
    -1.19
     economically
    -1.18
    POSITIVE LOGITS
     Craigslist
    1.28
     Slack
    1.23
    locks
    1.18
    Scot
    1.17
    cs
    1.16
     Webs
    1.15
     Berks
    1.14
     Verb
    1.13
     911
    1.12
     Delete
    1.09
    Activations Density 0.060%

    No Known Activations