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. 10245
    Prev
    Next
    INDEX
    Explanations

    statements or assertions regarding commitments or important declarations

    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
    0:0.04
    1:0.08
    2:0.12
    3:0.20
    4:0.05
    5:0.08
    6:0.07
    7:0.08
    8:0.07
    9:0.04
    10:0.07
    11:0.06
    Negative Logits
    Downloadha
    -1.31
     MIA
    -1.17
    lier
    -1.17
     enclave
    -1.14
     Makoto
    -1.14
     Laksh
    -1.14
     vulner
    -1.14
     Jiu
    -1.13
     territorial
    -1.09
    geries
    -1.09
    POSITIVE LOGITS
    sure
    1.39
    ️
    1.35
    lycer
    1.32
    vae
    1.30
    Ther
    1.26
    redible
    1.24
    idated
    1.23
    :(
    1.19
    redibly
    1.18
    Heart
    1.18
    Activations Density 0.087%

    No Known Activations