© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 21692
    Prev
    Next
    INDEX
    Explanations

    phrases and discussions about the concept of impact, particularly in various contexts such as relationships, economics, and societal issues

    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
    2:0.11
    3:0.08
    4:0.04
    5:0.13
    6:0.02
    7:0.04
    8:0.16
    9:0.18
    10:0.07
    11:0.03
    Negative Logits
    ointed
    -1.46
    ategory
    -1.38
     cass
    -1.19
     mosqu
    -1.16
    hin
    -1.13
    aughed
    -1.09
    ournal
    -1.07
    OHN
    -1.03
    inosaur
    -1.02
    ossier
    -1.02
    POSITIVE LOGITS
    ーテ
    1.49
     awa
    1.07
    efficiency
    1.05
     morale
    1.01
    abol
    0.99
     Strongh
    0.98
     undue
    0.98
     outweigh
    0.98
     Industries
    0.97
    selection
    0.97
    Activations Density 0.035%

    No Known Activations