© 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. 5-ATT-KK
    11. 43724
    Prev
    Next
    INDEX
    Explanations

    conjunctions, particularly the word "And."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.17
    1:0.13
    2:0.06
    3:0.04
    4:0.04
    5:0.07
    6:0.04
    7:0.02
    8:0.17
    9:0.08
    10:0.05
    11:0.07
    Negative Logits
    saf
    -1.62
    FIX
    -1.47
    Rh
    -1.40
    icent
    -1.33
    Boss
    -1.33
    ventures
    -1.32
    ocial
    -1.30
     Luxem
    -1.29
    Track
    -1.28
    eport
    -1.27
    POSITIVE LOGITS
    iqueness
    1.41
     someday
    1.33
    ersion
    1.32
     dunno
    1.32
     Hebdo
    1.27
     nobody
    1.26
     rationality
    1.26
     Allah
    1.23
     Divinity
    1.20
     displ
    1.18
    Activations Density 0.034%

    No Known Activations