© 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. 7603
    Prev
    Next
    INDEX
    Explanations

    expressions of rights and permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    1:0.02
    2:0.13
    3:0.05
    4:0.07
    5:0.02
    6:0.04
    7:0.35
    8:0.03
    9:0.03
    10:0.09
    11:0.09
    Negative Logits
    effic
    -1.65
    MRI
    -1.59
    eteenth
    -1.46
    flows
    -1.41
     Faust
    -1.41
     Fernand
    -1.39
    cock
    -1.39
     revolving
    -1.35
    olved
    -1.34
    cule
    -1.32
    POSITIVE LOGITS
     Choice
    1.48
    qualified
    1.47
     Vote
    1.42
     veto
    1.41
     chance
    1.40
    Alert
    1.38
     qualified
    1.37
     qualify
    1.33
     declare
    1.32
     Quit
    1.32
    Activations Density 0.004%

    No Known Activations