© 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. 5-ATT-KK
    11. 37363
    Prev
    Next
    INDEX
    Explanations

    significant events or keywords related to competitions or drafts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.08
    3:0.06
    4:0.07
    5:0.03
    6:0.36
    7:0.11
    8:0.03
    9:0.03
    10:0.09
    11:0.07
    Negative Logits
    eret
    -1.66
    anan
    -1.21
    urat
    -1.20
     Christensen
    -1.19
     Fortune
    -1.18
     mirrors
    -1.16
    inem
    -1.13
     Presbyterian
    -1.13
    erella
    -1.12
    ashtra
    -1.11
    POSITIVE LOGITS
    ciation
    1.52
    imester
    1.35
    jury
    1.29
    rations
    1.28
    ration
    1.25
    irements
    1.24
     fateful
    1.23
    �
    1.17
    ighting
    1.17
    charge
    1.16
    Activations Density 0.014%

    No Known Activations