© 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. 44138
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
    0:0.02
    1:0.02
    2:0.08
    3:0.04
    4:0.06
    5:0.02
    6:0.24
    7:0.12
    8:0.03
    9:0.03
    10:0.24
    11:0.05
    Negative Logits
    ㅋㅋ
    -1.78
    autions
    -1.74
    アル
    -1.74
    ------------
    -1.73
    カ
    -1.73
    EFF
    -1.67
    Child
    -1.65
    �
    -1.64
    チ
    -1.62
    isSpecialOrderable
    -1.61
    POSITIVE LOGITS
     fences
    1.72
     fencing
    1.70
     ledger
    1.66
     terminals
    1.65
     sediment
    1.64
     corridor
    1.62
     machinery
    1.61
     berth
    1.61
     pool
    1.61
     pathogens
    1.61
    Activations Density 0.000%

    No Known Activations