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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 628
    Prev
    Next
    INDEX
    Explanations

    the article "a."

    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
    0:0.08
    1:0.08
    2:0.08
    3:0.08
    4:0.08
    5:0.09
    6:0.06
    7:0.08
    8:0.08
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
    ilitary
    -3.13
    FN
    -3.05
    unta
    -2.83
    PRES
    -2.69
    icist
    -2.66
     Sabha
    -2.63
     Gors
    -2.59
    rail
    -2.57
    arag
    -2.56
    orses
    -2.54
    POSITIVE LOGITS
     slowed
    3.54
    ijn
    3.16
     slower
    3.00
     bounces
    2.87
     metrics
    2.83
     bounce
    2.77
     jams
    2.72
     slows
    2.63
     paused
    2.63
     halted
    2.56
    Activations Density 0.000%

    No Known Activations