© 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. 4540
    Prev
    Next
    INDEX
    Explanations

    phrases indicating release or dismissal

    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
    0:0.02
    1:0.01
    2:0.05
    3:0.05
    4:0.05
    5:0.03
    6:0.09
    7:0.11
    8:0.05
    9:0.03
    10:0.06
    11:0.39
    Negative Logits
     scalp
    -2.08
     whirlwind
    -2.04
     Rune
    -2.02
     adren
    -2.01
     physique
    -1.95
     hype
    -1.95
     smile
    -1.90
     platinum
    -1.89
     steroid
    -1.87
     adrenaline
    -1.86
    POSITIVE LOGITS
    Neigh
    2.31
     sidx
    2.21
    ittees
    2.17
     WRITE
    2.11
    ocument
    2.08
     dissenting
    2.07
    vice
    2.07
     neighbor
    2.05
    utherford
    2.05
    SPONSORED
    1.99
    Activations Density 0.000%

    No Known Activations