© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 7222
    Prev
    Next
    INDEX
    Explanations

    key concepts and arguments within discussions

    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
    0:0.02
    1:0.09
    2:0.21
    3:0.04
    4:0.01
    5:0.04
    6:0.08
    7:0.09
    8:0.16
    9:0.10
    10:0.05
    11:0.05
    Negative Logits
     budgets
    -1.16
     Images
    -1.10
     Alban
    -1.10
     Cancel
    -1.09
     Format
    -1.09
     [|
    -1.08
     Prix
    -1.07
    士
    -1.06
    etsk
    -1.05
     }}
    -1.03
    POSITIVE LOGITS
    GAME
    1.38
    atcher
    1.31
    eworld
    1.31
    nah
    1.30
    hest
    1.29
     inherent
    1.26
    saf
    1.25
    liest
    1.24
    onite
    1.24
    undrum
    1.21
    Activations Density 0.044%

    No Known Activations