© 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. 10-ATT-KK
    11. 22387
    Prev
    Next
    INDEX
    Explanations

    technical terms related to web technology and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    3:0.04
    4:0.04
    5:0.25
    6:0.02
    7:0.03
    8:0.02
    9:0.37
    10:0.02
    11:0.08
    Negative Logits
     worst
    -2.69
    worst
    -2.58
    best
    -2.53
    fax
    -2.43
     deadliest
    -2.42
     least
    -2.36
     strongest
    -2.28
     hardest
    -2.23
     safest
    -2.20
    wikipedia
    -2.18
    POSITIVE LOGITS
     than
    4.11
     Than
    3.50
    than
    3.33
    ypes
    2.69
    acements
    2.44
    oppers
    2.37
    !]
    2.23
    worldly
    2.22
     LIKE
    2.20
     ACTIONS
    2.19
    Activations Density 0.157%

    No Known Activations