© 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. 10-ATT-KK
    11. 21500
    Prev
    Next
    INDEX
    Explanations

    negative experiences or difficulties encountered

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.11
    2:0.06
    3:0.08
    4:0.07
    5:0.05
    6:0.13
    7:0.09
    8:0.05
    9:0.06
    10:0.08
    11:0.09
    Negative Logits
     pled
    -2.88
     Sail
    -2.58
    Wal
    -2.42
    Stra
    -2.35
     Shell
    -2.31
     Spartan
    -2.30
     Sel
    -2.28
    Shell
    -2.25
    VEL
    -2.25
     NET
    -2.24
    POSITIVE LOGITS
     interference
    4.08
     interfering
    3.98
     interfere
    3.23
     interfered
    3.14
     meddling
    3.02
     interf
    2.84
    scill
    2.68
     Leilan
    2.66
    iott
    2.64
    isphere
    2.55
    Activations Density 0.000%

    No Known Activations