© 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. 2-ATT-KK
    11. 22080
    Prev
    Next
    INDEX
    Explanations

    names of individuals or proper nouns related to specific people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.09
    3:0.06
    4:0.09
    5:0.09
    6:0.03
    7:0.09
    8:0.08
    9:0.08
    10:0.16
    11:0.10
    Negative Logits
     suspic
    -1.02
     cryst
    -0.84
     reluct
    -0.82
     Rove
    -0.80
     pony
    -0.80
     millenn
    -0.79
     corrid
    -0.79
    Pg
    -0.78
     enthusi
    -0.78
     unfavorable
    -0.78
    POSITIVE LOGITS
    oglu
    1.08
     III
    1.05
    ensis
    1.03
     Aut
    0.97
    angan
    0.95
    abis
    0.90
    uala
    0.88
    allas
    0.88
     Parish
    0.86
    uminium
    0.86
    Activations Density 0.585%

    No Known Activations