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. 9-ATT-KK
    6. 7581
    Prev
    Next
    INDEX
    Explanations

    instances of the word "down"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.09
    2:0.08
    3:0.09
    4:0.06
    5:0.08
    6:0.08
    7:0.08
    8:0.06
    9:0.07
    10:0.10
    11:0.08
    Negative Logits
    merce
    -3.49
    aples
    -2.88
    umenthal
    -2.69
    licks
    -2.65
    ointment
    -2.60
     rotten
    -2.58
    HUD
    -2.58
    afort
    -2.57
     dive
    -2.54
     ashes
    -2.48
    POSITIVE LOGITS
     Breed
    2.62
    tera
    2.60
     Mobility
    2.45
     Unique
    2.40
     Tat
    2.33
     Polo
    2.32
     Transport
    2.31
     scarf
    2.31
     Licensed
    2.30
     Rik
    2.29
    Activations Density 0.000%

    No Known Activations