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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 18769
    Prev
    Next
    INDEX
    Explanations

    references to the ongoing conflict in Syria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.06
    2:0.01
    3:0.12
    4:0.03
    5:0.30
    6:0.10
    7:0.03
    8:0.10
    9:0.11
    10:0.01
    11:0.01
    Negative Logits
    ensor
    -2.18
    atcher
    -2.10
     retracted
    -2.07
    Attach
    -2.06
    idav
    -2.04
    ��
    -2.00
    etus
    -1.93
     recons
    -1.76
    final
    -1.76
    othal
    -1.75
    POSITIVE LOGITS
     bustling
    2.69
    mopolitan
    2.56
     thriving
    2.40
     winters
    2.38
     amenities
    2.38
     populous
    2.26
     vibrant
    2.24
    population
    2.24
     limestone
    2.22
     prosperous
    2.20
    Activations Density 1.087%

    No Known Activations