© 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. 43979
    Prev
    Next
    INDEX
    Explanations

    the word "that" and other general connectors or qualifying terms in the text

    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
    0:0.03
    1:0.01
    2:0.13
    3:0.05
    4:0.15
    5:0.03
    6:0.04
    7:0.30
    8:0.06
    9:0.03
    10:0.05
    11:0.07
    Negative Logits
    esters
    -2.29
    ester
    -1.96
    forts
    -1.78
    uel
    -1.75
    eger
    -1.65
    plets
    -1.60
     Lans
    -1.60
    users
    -1.53
    ographers
    -1.50
    uries
    -1.48
    POSITIVE LOGITS
     direction
    1.86
     allegiance
    1.76
     posture
    1.55
     belief
    1.55
     regard
    1.51
     stance
    1.51
     knots
    1.50
     outlook
    1.50
     affirmation
    1.50
     refusal
    1.49
    Activations Density 0.001%

    No Known Activations