© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 20544
    Prev
    Next
    INDEX
    Explanations

    time indicators in the text

    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
    0:0.05
    1:0.03
    2:0.04
    3:0.15
    4:0.04
    5:0.10
    6:0.04
    7:0.06
    8:0.10
    9:0.03
    10:0.27
    11:0.03
    Negative Logits
    BBC
    -2.27
    TIT
    -2.16
     scept
    -2.01
    stood
    -1.98
    wart
    -1.93
    warts
    -1.92
     envis
    -1.91
     impunity
    -1.91
     moderately
    -1.90
     Channel
    -1.86
    POSITIVE LOGITS
    ciation
    2.17
     Correction
    2.02
    :]
    2.00
    endix
    1.95
     corrected
    1.92
    rises
    1.86
     particulars
    1.86
     replacements
    1.85
     rebutt
    1.79
    adesh
    1.77
    Activations Density 0.019%

    No Known Activations