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. 9514
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to threats and confrontations

    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
    0:0.04
    1:0.06
    2:0.18
    3:0.05
    4:0.04
    5:0.03
    6:0.04
    7:0.05
    8:0.04
    9:0.04
    10:0.33
    11:0.05
    Negative Logits
    >>>
    -2.78
    rika
    -2.43
    rov
    -2.43
    viol
    -2.35
    ivari
    -2.29
    ===
    -2.28
    UTC
    -2.27
    oti
    -2.25
    00000
    -2.23
    vette
    -2.21
    POSITIVE LOGITS
    head
    4.05
     Head
    3.83
    HEAD
    3.64
     head
    3.50
     heads
    3.41
     Heads
    3.40
    Head
    3.38
    heads
    3.16
     HEAD
    3.07
    headed
    2.95
    Activations Density 0.002%

    No Known Activations