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

    Neuronpedia

    Jacobian LensNEW
    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. 10-ATT-KK
    11. 21230
    Prev
    Next
    INDEX
    Explanations

    negations and contrasting conjunctions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.16
    2:0.06
    3:0.04
    4:0.08
    5:0.06
    6:0.05
    7:0.13
    8:0.06
    9:0.07
    10:0.04
    11:0.16
    Negative Logits
     microbial
    -2.52
     incorpor
    -2.24
     incorporation
    -2.21
     qualitative
    -2.21
     indirect
    -2.16
    ormon
    -2.12
    estial
    -2.07
     disguise
    -2.05
     additions
    -2.04
     Subst
    -2.01
    POSITIVE LOGITS
     nobody
    3.17
     Nobody
    3.00
    Nobody
    2.98
    ateurs
    2.78
     nowhere
    2.68
    everyone
    2.56
    except
    2.43
     Everybody
    2.27
    nob
    2.23
    ppa
    2.23
    Activations Density 0.001%

    No Known Activations