© 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. 22730
    Prev
    Next
    INDEX
    Explanations

    entities mentioned in a bureaucratic or legal context

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

    references to locations and geographic entities

    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
    1:0.01
    2:0.14
    3:0.08
    4:0.04
    5:0.12
    6:0.07
    7:0.07
    8:0.06
    9:0.07
    10:0.13
    11:0.06
    Negative Logits
    SPONSORED
    -0.93
    #$
    -0.90
    ..."
    -0.90
    Magikarp
    -0.73
     bell
    -0.72
    nih
    -0.71
     Millenn
    -0.71
    assets
    -0.71
    natureconservancy
    -0.71
     lif
    -0.70
    POSITIVE LOGITS
     Detail
    0.99
    theless
    0.94
    FIELD
    0.88
     Conclusion
    0.86
    wich
    0.86
     Appeal
    0.84
    autions
    0.84
    udos
    0.84
    anwhile
    0.83
     Extensions
    0.82
    Activations Density 0.228%

    No Known Activations