© 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. 43871
    Prev
    Next
    INDEX
    Explanations

    instances of personal experiences and evaluations

    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
    0:0.01
    1:0.01
    2:0.36
    3:0.23
    4:0.06
    5:0.03
    6:0.02
    7:0.02
    8:0.04
    9:0.05
    10:0.05
    11:0.06
    Negative Logits
    eteen
    -2.02
    SPONSORED
    -1.71
    OHN
    -1.65
    illac
    -1.61
    ascar
    -1.60
    stanbul
    -1.58
    orkshire
    -1.57
    apsed
    -1.56
    orescent
    -1.51
    ּ
    -1.50
    POSITIVE LOGITS
     nonetheless
    1.63
     ensures
    1.54
     accordingly
    1.53
     ensured
    1.51
     Reboot
    1.47
     ensure
    1.36
     shalt
    1.35
     nevertheless
    1.33
     maximize
    1.32
     guessing
    1.31
    Activations Density 0.034%

    No Known Activations