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. 43971
    Prev
    Next
    INDEX
    Explanations

    instances of the word "accommodate" and contexts related to accommodating individuals or groups, particularly in a workplace or social setting

    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
    0:0.01
    1:0.01
    2:0.04
    3:0.06
    4:0.26
    5:0.02
    6:0.03
    7:0.36
    8:0.03
    9:0.02
    10:0.06
    11:0.06
    Negative Logits
    grave
    -1.63
    arta
    -1.61
    ModLoader
    -1.60
    Wikipedia
    -1.52
    Upload
    -1.50
    chieve
    -1.49
    wikipedia
    -1.49
    ibur
    -1.48
     awa
    -1.48
    ename
    -1.45
    POSITIVE LOGITS
     workload
    1.69
     influx
    1.59
     newcomers
    1.58
     whims
    1.56
     conting
    1.51
     loads
    1.45
     incoming
    1.45
     snug
    1.43
     loan
    1.42
     needs
    1.42
    Activations Density 0.003%

    No Known Activations