© 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. 9-ATT-KK
    11. 24212
    Prev
    Next
    INDEX
    Explanations

    time-related expressions and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.35
    2:0.04
    3:0.07
    4:0.03
    5:0.10
    6:0.03
    7:0.07
    8:0.07
    9:0.04
    10:0.08
    11:0.03
    Negative Logits
     longest
    -2.82
     74
    -2.73
    "]=>
    -2.71
     1980
    -2.63
    Ranked
    -2.58
     1971
    -2.54
    Seven
    -2.53
     73
    -2.52
     144
    -2.52
     twice
    -2.52
    POSITIVE LOGITS
    simple
    3.15
    ief
    3.13
     simply
    2.93
     lowly
    2.84
    ionics
    2.82
     needless
    2.70
     simple
    2.58
     arrog
    2.54
    ensing
    2.53
    Initial
    2.51
    Activations Density 0.005%

    No Known Activations