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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 44445
    Prev
    Next
    INDEX
    Explanations

    instances of the word "air."

    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
    1:0.06
    2:0.07
    3:0.05
    4:0.06
    5:0.07
    6:0.05
    7:0.06
    8:0.06
    9:0.07
    10:0.26
    11:0.10
    Negative Logits
    EY
    -1.61
     Cardinal
    -1.59
    =$
    -1.59
     Rothschild
    -1.58
    Accessory
    -1.56
    folio
    -1.54
     HSBC
    -1.51
     browse
    -1.50
    :\
    -1.50
    laus
    -1.48
    POSITIVE LOGITS
    interstitial
    2.01
    ikuman
    1.86
     announ
    1.71
    ��
    1.71
     polic
    1.69
     ozone
    1.65
    imeters
    1.63
    jriwal
    1.62
    inson
    1.61
    estic
    1.55
    Activations Density 0.000%

    No Known Activations