© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 5678
    Prev
    Next
    INDEX
    Explanations

    instances of discovery or revelation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.06
    2:0.06
    3:0.02
    4:0.11
    5:0.24
    6:0.05
    7:0.06
    8:0.05
    9:0.06
    10:0.11
    11:0.06
    Negative Logits
     inherently
    -1.87
     intrinsically
    -1.80
     proven
    -1.78
     evolution
    -1.73
     Inher
    -1.71
     additive
    -1.67
     Context
    -1.64
     merit
    -1.64
     intrinsic
    -1.62
     longevity
    -1.59
    POSITIVE LOGITS
    FTWARE
    2.03
    livious
    1.82
    quit
    1.80
    looking
    1.79
    then
    1.77
    later
    1.76
    Suddenly
    1.73
    upon
    1.71
    HEAD
    1.71
    IRC
    1.70
    Activations Density 0.817%

    No Known Activations