© 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. 44147
    Prev
    Next
    INDEX
    Explanations

    instances of the word "until."

    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
    2:0.05
    3:0.07
    4:0.16
    5:0.03
    6:0.12
    7:0.06
    8:0.06
    9:0.03
    10:0.07
    11:0.25
    Negative Logits
     coli
    -1.86
     Chronic
    -1.62
    "/>
    -1.59
    tan
    -1.56
     delinquent
    -1.53
    }"
    -1.52
    *.
    -1.50
     hereafter
    -1.50
    .>>
    -1.49
     Sabb
    -1.47
    POSITIVE LOGITS
    livious
    2.46
    iator
    1.92
    aughs
    1.80
    leans
    1.80
    reet
    1.75
     teasp
    1.71
    undai
    1.69
    affles
    1.68
    gettable
    1.60
    uador
    1.59
    Activations Density 0.001%

    No Known Activations