© 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. 5-ATT-KK
    11. 42425
    Prev
    Next
    INDEX
    Explanations

    statistical measures and numerical data

    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
    0:0.09
    1:0.05
    2:0.16
    3:0.08
    4:0.10
    5:0.06
    6:0.06
    7:0.02
    8:0.07
    9:0.09
    10:0.07
    11:0.09
    Negative Logits
    kef
    -1.61
    Interstitial
    -1.50
    Reviewer
    -1.47
    ocument
    -1.34
    unicip
    -1.31
     Volunte
    -1.25
    eday
    -1.24
    ipel
    -1.23
    utor
    -1.20
    mpeg
    -1.20
    POSITIVE LOGITS
     Vegeta
    1.32
     TOTAL
    1.30
     ammo
    1.23
     weaponry
    1.22
     ammunition
    1.19
     firepower
    1.18
    ↑
    1.11
     hits
    1.11
     sockets
    1.11
    uces
    1.08
    Activations Density 0.007%

    No Known Activations