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. 3-ATT-KK
    6. 10702
    Prev
    Next
    INDEX
    Explanations

    phrases and references related to division and unity within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.09
    3:0.25
    4:0.01
    5:0.03
    6:0.06
    7:0.13
    8:0.09
    9:0.09
    10:0.05
    11:0.12
    Negative Logits
    idon
    -1.39
    gets
    -1.32
    bye
    -1.26
    ogle
    -1.12
    ォ
    -1.11
    nor
    -1.11
    god
    -1.10
    eport
    -1.10
    ilyn
    -1.08
    ipt
    -1.07
    POSITIVE LOGITS
    arus
    1.22
     Marketable
    1.19
    oxide
    1.15
    ebook
    1.15
     spo
    1.12
     oxide
    1.12
    ombat
    1.08
     Kashmir
    1.08
    US
    1.08
    cius
    1.08
    Activations Density 0.008%

    No Known Activations