© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10513
    Prev
    Next
    INDEX
    Explanations

    user profile-related information

    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
    0:0.20
    1:0.04
    2:0.05
    3:0.11
    4:0.05
    5:0.21
    6:0.03
    7:0.08
    8:0.04
    9:0.02
    10:0.08
    11:0.05
    Negative Logits
    Buzz
    -2.23
     toolbar
    -2.04
    Python
    -2.03
    laim
    -2.03
     licens
    -1.98
    rex
    -1.93
     attribution
    -1.91
    �
    -1.88
    ospace
    -1.87
    aughs
    -1.85
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    2.65
    culosis
    2.10
    nesium
    2.02
     coli
    2.00
     Spectre
    1.99
     halluc
    1.98
    patient
    1.96
     FW
    1.93
    ranean
    1.91
     Mushroom
    1.90
    Activations Density 0.003%

    No Known Activations