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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11485
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and development

    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
    0:0.04
    1:0.05
    2:0.04
    3:0.06
    4:0.04
    5:0.03
    6:0.16
    7:0.02
    8:0.06
    9:0.36
    10:0.03
    11:0.04
    Negative Logits
     Amtrak
    -4.08
     Piper
    -3.99
     Boehner
    -3.79
     Brewer
    -3.73
     coworkers
    -3.70
     airplane
    -3.63
    defense
    -3.60
     Wagner
    -3.59
     Dickinson
    -3.51
     Pelosi
    -3.48
    POSITIVE LOGITS
     mould
    6.00
     armour
    5.52
     licence
    5.50
     licences
    5.27
    colour
    5.14
     analys
    5.06
     arte
    5.01
     realised
    4.97
     centres
    4.96
     metres
    4.92
    Activations Density 0.045%

    No Known Activations