© 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. 9-ATT-KK
    11. 22926
    Prev
    Next
    INDEX
    Explanations

    time indicators and date-related references

    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
    0:0.02
    1:0.38
    2:0.03
    3:0.06
    4:0.03
    5:0.07
    6:0.03
    7:0.08
    8:0.04
    9:0.10
    10:0.04
    11:0.06
    Negative Logits
    erest
    -2.69
    110
    -2.46
     118
    -2.43
     109
    -2.41
    111
    -2.39
    ever
    -2.39
    177
    -2.38
     welf
    -2.35
    grim
    -2.35
    1111
    -2.34
    POSITIVE LOGITS
    ruary
    3.37
    February
    3.13
     February
    2.95
    ensional
    2.82
     sometime
    2.81
    rahim
    2.76
    代
    2.70
    icka
    2.66
    tesy
    2.62
    thank
    2.57
    Activations Density 0.005%

    No Known Activations