© 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. 8811
    Prev
    Next
    INDEX
    Explanations

    words associated with technology and systems security

    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
    1:0.03
    2:0.04
    3:0.37
    4:0.02
    5:0.02
    6:0.04
    7:0.17
    8:0.04
    9:0.09
    10:0.06
    11:0.06
    Negative Logits
    ️
    -1.61
    idon
    -1.48
    odan
    -1.43
    Unix
    -1.35
    oslav
    -1.28
    UGE
    -1.26
    ��
    -1.26
    andowski
    -1.24
    SpaceEngineers
    -1.23
    odo
    -1.22
    POSITIVE LOGITS
    jee
    1.29
    iser
    1.17
    女
    1.16
     vacc
    1.16
     picnic
    1.16
     delve
    1.15
     confir
    1.15
    bender
    1.08
    atu
    1.08
    igham
    1.07
    Activations Density 0.009%

    No Known Activations