© 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. 9739
    Prev
    Next
    INDEX
    Explanations

    significant numerical values and phrases indicating quantity or percentage

    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
    1:0.04
    2:0.07
    3:0.04
    4:0.02
    5:0.07
    6:0.05
    7:0.35
    8:0.07
    9:0.09
    10:0.07
    11:0.06
    Negative Logits
     ACTIONS
    -1.48
    pmwiki
    -1.46
    vous
    -1.37
     encount
    -1.28
    ARDS
    -1.24
    heim
    -1.21
    ERT
    -1.20
     CTR
    -1.19
    IRC
    -1.18
    zik
    -1.17
    POSITIVE LOGITS
     Otto
    1.42
     Eden
    1.25
    ende
    1.18
     Frem
    1.14
     Plymouth
    1.14
     Lucy
    1.13
     Marqu
    1.11
     captivity
    1.09
     ape
    1.09
     enslaved
    1.08
    Activations Density 0.023%

    No Known Activations