© 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. 22869
    Prev
    Next
    INDEX
    Explanations

    communication actions, such as emailing and texting

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

    instances of communication or requests for information via email or text

    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
    1:0.03
    2:0.08
    3:0.08
    4:0.07
    5:0.09
    6:0.04
    7:0.03
    8:0.22
    9:0.14
    10:0.07
    11:0.02
    Negative Logits
    peat
    -1.30
    ahime
    -1.15
     Conclusion
    -1.14
    define
    -1.14
     horizon
    -1.13
    represented
    -1.11
     ===
    -1.10
     Tradable
    -1.08
     stride
    -1.06
     dominion
    -1.05
    POSITIVE LOGITS
     Pastebin
    1.34
    unia
    1.34
    NSA
    1.18
    Scot
    1.17
     spor
    1.17
    idav
    1.16
    apa
    1.11
     "@
    1.11
    Ott
    1.10
    andum
    1.10
    Activations Density 0.006%

    No Known Activations