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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10352
    Prev
    Next
    INDEX
    Explanations

    references to healthcare policies and social issues

    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
    1:0.11
    2:0.12
    3:0.04
    4:0.06
    5:0.09
    6:0.11
    7:0.08
    8:0.07
    9:0.06
    10:0.10
    11:0.07
    Negative Logits
    ealous
    -1.45
    astical
    -1.40
    mbuds
    -1.29
    bda
    -1.28
    heimer
    -1.24
    etheless
    -1.24
    pard
    -1.22
    umers
    -1.19
    ducers
    -1.19
    artney
    -1.19
    POSITIVE LOGITS
     �
    1.29
    ビ
    1.15
     裏�
    1.13
    BuyableInstoreAndOnline
    1.10
     etc
    1.05
    ヘ
    1.00
     max
    1.00
     sleeps
    0.99
     Nanto
    0.98
    "}],"
    0.98
    Activations Density 1.290%

    No Known Activations