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. 10996
    Prev
    Next
    INDEX
    Explanations

    mentions of media categories or sections within publications

    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
    0:0.09
    1:0.02
    2:0.03
    3:0.23
    4:0.04
    5:0.10
    6:0.03
    7:0.09
    8:0.05
    9:0.02
    10:0.16
    11:0.08
    Negative Logits
     resumed
    -2.43
     disbanded
    -2.37
     supervised
    -2.31
     resusc
    -2.27
     reopened
    -2.27
     rede
    -2.15
     expired
    -2.12
     rebuilt
    -2.10
     reconstructed
    -2.08
     indefinite
    -2.07
    POSITIVE LOGITS
     Deals
    2.31
     Concern
    2.28
     Tags
    2.26
    ategories
    2.21
     Addiction
    2.19
     Interest
    2.17
     Everywhere
    2.12
    isite
    2.07
     Countries
    2.04
     Attention
    2.04
    Activations Density 0.001%

    No Known Activations