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. 9997
    Prev
    Next
    INDEX
    Explanations

    names and terms related to people and locations

    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
    1:0.04
    2:0.09
    3:0.27
    4:0.02
    5:0.02
    6:0.11
    7:0.09
    8:0.05
    9:0.11
    10:0.06
    11:0.07
    Negative Logits
    ascript
    -1.39
    ionage
    -1.37
    theless
    -1.20
    riott
    -1.17
    iferation
    -1.13
    ivably
    -1.10
    tyard
    -1.06
     Lazarus
    -1.05
    ilege
    -1.03
    phia
    -1.03
    POSITIVE LOGITS
     Lumpur
    1.44
    EStream
    1.41
    ikuman
    1.31
    EStreamFrame
    1.31
    ��
    1.24
    pie
    1.23
    inski
    1.22
    �
    1.19
    chuk
    1.15
    gow
    1.15
    Activations Density 0.030%

    No Known Activations