Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10656
    Prev
    Next
    INDEX
    Explanations

    references to statistical data or significant numerical changes

    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
    1:0.05
    2:0.07
    3:0.08
    4:0.05
    5:0.31
    6:0.06
    7:0.12
    8:0.04
    9:0.05
    10:0.05
    11:0.03
    Negative Logits
    urious
    -3.25
     Barcl
    -2.77
     adjustment
    -2.62
     Schr
    -2.61
    selage
    -2.59
    upper
    -2.57
     Lilly
    -2.48
     adjusting
    -2.48
    DAQ
    -2.47
     ~/.
    -2.45
    POSITIVE LOGITS
     Guer
    2.96
     canv
    2.92
    leground
    2.85
    Campaign
    2.78
     tribal
    2.78
     Tribal
    2.75
     Torrent
    2.74
    violence
    2.61
     campaigning
    2.59
    ampions
    2.58
    Activations Density 0.002%

    No Known Activations