© 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. 43953
    Prev
    Next
    INDEX
    Explanations

    phrases that express specific preferences or opinions

    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
    2:0.10
    3:0.06
    4:0.06
    5:0.03
    6:0.06
    7:0.39
    8:0.04
    9:0.04
    10:0.08
    11:0.06
    Negative Logits
     Valhalla
    -1.79
     Suite
    -1.69
    inav
    -1.67
     Symbol
    -1.63
     unification
    -1.57
     Walls
    -1.56
    Unity
    -1.53
     Neuroscience
    -1.50
     Statue
    -1.49
     srfAttach
    -1.49
    POSITIVE LOGITS
     cull
    1.83
    emouth
    1.80
     lett
    1.79
     offend
    1.73
    ppe
    1.67
     vying
    1.66
     enqu
    1.59
     pests
    1.56
     assail
    1.55
     lest
    1.53
    Activations Density 0.000%

    No Known Activations