© 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. 41786
    Prev
    Next
    INDEX
    Explanations

    quantities related to performance and achievement metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.18
    1:0.07
    2:0.04
    3:0.05
    4:0.03
    5:0.08
    6:0.04
    7:0.01
    8:0.37
    9:0.03
    10:0.02
    11:0.02
    Negative Logits
     horizont
    -1.65
     coerc
    -1.61
     sidx
    -1.54
     liter
    -1.48
     incorpor
    -1.42
     seq
    -1.37
     Mobil
    -1.37
     Elev
    -1.34
     errone
    -1.34
     typo
    -1.34
    POSITIVE LOGITS
    been
    2.54
    fur
    1.93
    shut
    1.89
    eni
    1.77
    she
    1.75
    eto
    1.74
    were
    1.72
    uno
    1.72
    da
    1.72
    mean
    1.67
    Activations Density 0.114%

    No Known Activations