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. 5-ATT-KK
    6. 43489
    Prev
    Next
    INDEX
    Explanations

    instances of actions or events caused by bombs or bombing activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.01
    2:0.09
    3:0.05
    4:0.19
    5:0.02
    6:0.04
    7:0.24
    8:0.03
    9:0.03
    10:0.11
    11:0.11
    Negative Logits
    izons
    -1.96
    assies
    -1.94
    mbuds
    -1.86
    ffic
    -1.78
    anooga
    -1.75
    dds
    -1.70
    osponsors
    -1.68
    ��
    -1.68
    geon
    -1.63
    verning
    -1.62
    POSITIVE LOGITS
     irregularities
    1.67
     rather
    1.66
     whims
    1.58
     Kah
    1.56
     lingering
    1.53
     crashes
    1.52
     laz
    1.50
     falling
    1.50
     disturbance
    1.48
     pecul
    1.48
    Activations Density 0.007%

    No Known Activations