© 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. 43697
    Prev
    Next
    INDEX
    Explanations

    references to scientific phenomena and experimental setups

    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
    0:0.02
    1:0.01
    2:0.24
    3:0.09
    4:0.09
    5:0.03
    6:0.03
    7:0.09
    8:0.06
    9:0.04
    10:0.16
    11:0.09
    Negative Logits
     sqor
    -1.83
    adiq
    -1.64
    reci
    -1.58
    uer
    -1.57
    akings
    -1.55
    initions
    -1.54
    roy
    -1.51
    appings
    -1.50
    20439
    -1.47
    aldi
    -1.47
    POSITIVE LOGITS
     presided
    1.69
     consisting
    1.61
     overseen
    1.60
     supplemented
    1.59
     confines
    1.57
     reminiscent
    1.53
     Called
    1.52
     styled
    1.51
    livious
    1.46
     attic
    1.44
    Activations Density 0.318%

    No Known Activations