© 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. 27825
    Prev
    Next
    INDEX
    Explanations

    specific names and terms related to technology and science

    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
    2:0.10
    3:0.28
    4:0.26
    5:0.02
    6:0.04
    7:0.03
    8:0.04
    9:0.03
    10:0.06
    11:0.04
    Negative Logits
     cannot
    -1.89
    untarily
    -1.86
    alysed
    -1.79
    」
    -1.79
    Material
    -1.78
    ilib
    -1.77
    iliated
    -1.77
    ifies
    -1.77
    annot
    -1.73
    Correct
    -1.73
    POSITIVE LOGITS
     Nurs
    2.10
     Schn
    1.83
     HG
    1.75
     Hip
    1.70
    ?).
    1.69
     Sting
    1.69
     Alz
    1.65
    !).
    1.56
     Antar
    1.56
     Mour
    1.55
    Activations Density 0.007%

    No Known Activations