© 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. 26296
    Prev
    Next
    INDEX
    Explanations

    references to specific media and academic works, particularly in programming and engineering contexts

    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
    0:0.03
    1:0.04
    2:0.09
    3:0.19
    4:0.11
    5:0.08
    6:0.04
    7:0.04
    8:0.07
    9:0.10
    10:0.11
    11:0.06
    Negative Logits
     hurting
    -1.64
     disproportionately
    -1.63
     uncontroll
    -1.49
     detriment
    -1.43
     breathing
    -1.43
     needy
    -1.42
     depend
    -1.41
     contam
    -1.41
     inappropriately
    -1.41
     prey
    -1.39
    POSITIVE LOGITS
    田
    1.71
    ipedia
    1.57
     archives
    1.55
     Archives
    1.52
    Blog
    1.51
     Architects
    1.50
    .).
    1.49
    Research
    1.47
    forum
    1.45
    ーン
    1.45
    Activations Density 0.767%

    No Known Activations