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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 44313
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "and" in various contexts

    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
    2:0.08
    3:0.07
    4:0.10
    5:0.02
    6:0.09
    7:0.25
    8:0.04
    9:0.03
    10:0.15
    11:0.08
    Negative Logits
    IGN
    -1.70
    20439
    -1.68
    Maps
    -1.64
    ��
    -1.62
    lance
    -1.59
    Commerce
    -1.55
    express
    -1.54
    omever
    -1.53
    覚醒
    -1.53
    eele
    -1.49
    POSITIVE LOGITS
     coma
    2.15
     uncontroll
    1.70
     dehydration
    1.70
     suicide
    1.68
     tears
    1.67
     sob
    1.64
     spir
    1.61
     sleep
    1.60
     lung
    1.58
     Resurrection
    1.58
    Activations Density 0.002%

    No Known Activations