© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43085
    Prev
    Next
    INDEX
    Explanations

    instances of the word "busy."

    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
    1:0.02
    2:0.06
    3:0.08
    4:0.16
    5:0.04
    6:0.08
    7:0.28
    8:0.04
    9:0.05
    10:0.06
    11:0.05
    Negative Logits
     characterized
    -1.65
     sclerosis
    -1.51
    anmar
    -1.48
     paths
    -1.47
     Ranked
    -1.46
    osponsors
    -1.45
     splits
    -1.45
     sugg
    -1.44
    フ
    -1.43
     financed
    -1.43
    POSITIVE LOGITS
    mast
    1.84
    amy
    1.73
    brate
    1.72
    thouse
    1.72
    lesiastical
    1.65
    urnal
    1.62
    tta
    1.60
    sein
    1.59
    lication
    1.57
    ordinary
    1.56
    Activations Density 0.000%

    No Known Activations