© 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. 10-ATT-KK
    11. 21435
    Prev
    Next
    INDEX
    Explanations

    numerical representations of time in timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.08
    2:0.25
    3:0.02
    4:0.41
    5:0.01
    6:0.02
    7:0.06
    8:0.01
    9:0.01
    10:0.04
    11:0.03
    Negative Logits
    channelAvailability
    -2.79
    ersed
    -2.72
    .","
    -2.56
    ',"
    -2.54
    Reviewed
    -2.54
    .""
    -2.49
    '."
    -2.45
    ospace
    -2.32
    ,'"
    -2.31
    ILLE
    -2.30
    POSITIVE LOGITS
    32
    3.01
    40
    2.98
    35
    2.97
    31
    2.91
    38
    2.91
    20
    2.88
    42
    2.86
    05
    2.81
    00
    2.81
    26
    2.80
    Activations Density 0.004%

    No Known Activations