© 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. 8107
    Prev
    Next
    INDEX
    Explanations

    terms related to anatomical structures and their specific expressions in neuronal cells

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.05
    1:0.04
    2:0.08
    3:0.09
    4:0.06
    5:0.08
    6:0.05
    7:0.05
    8:0.04
    9:0.16
    10:0.17
    11:0.10
    Negative Logits
    ampunk
    -1.35
     quir
    -1.34
     tatt
    -1.28
     outlaw
    -1.23
    humane
    -1.18
     diplomacy
    -1.18
     flair
    -1.17
     bribery
    -1.16
    LGBT
    -1.14
     booze
    -1.13
    POSITIVE LOGITS
    ⓘ
    1.32
     (−
    1.29
     magnitude
    1.28
     located
    1.27
     +/-
    1.26
     Hilbert
    1.26
     adjacent
    1.26
     ±
    1.25
     slope
    1.22
     indicated
    1.20
    Activations Density 0.043%

    No Known Activations