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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 21735
    Prev
    Next
    INDEX
    Explanations

    references to policies and decision-making processes

    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
    0:0.06
    1:0.03
    2:0.06
    3:0.06
    4:0.08
    5:0.06
    6:0.03
    7:0.03
    8:0.37
    9:0.07
    10:0.06
    11:0.03
    Negative Logits
     tackled
    -1.52
     flung
    -1.41
     swapped
    -1.37
     repaired
    -1.32
     honoured
    -1.31
     vetoed
    -1.30
     punished
    -1.30
     accounted
    -1.28
     impacted
    -1.28
     ushered
    -1.27
    POSITIVE LOGITS
     Paleo
    1.36
     proprietary
    1.36
    ULAR
    1.35
    advertisement
    1.34
     presupp
    1.31
    hz
    1.29
     Patreon
    1.29
    orically
    1.27
     Saying
    1.21
     Religion
    1.19
    Activations Density 0.005%

    No Known Activations