© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 34784
    Prev
    Next
    INDEX
    Explanations

    instances of the word "And" to identify conjunctions or continuations in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.15
    3:0.10
    4:0.09
    5:0.04
    6:0.03
    7:0.10
    8:0.12
    9:0.07
    10:0.06
    11:0.12
    Negative Logits
    ixt
    -1.50
    latest
    -1.48
    usk
    -1.48
    wagen
    -1.39
    ADRA
    -1.39
    uilt
    -1.37
    Miller
    -1.35
    Whit
    -1.33
    hon
    -1.31
    ftime
    -1.31
    POSITIVE LOGITS
     Response
    1.65
     Solitaire
    1.62
    heit
    1.56
     resistance
    1.54
     mathematics
    1.51
     responses
    1.46
    Publisher
    1.44
     relation
    1.44
     feedback
    1.42
     response
    1.39
    Activations Density 0.001%

    No Known Activations