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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 9099
    Prev
    Next
    INDEX
    Explanations

    specific names and identifiers related to individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.07
    2:0.15
    3:0.05
    4:0.03
    5:0.05
    6:0.06
    7:0.07
    8:0.05
    9:0.04
    10:0.28
    11:0.05
    Negative Logits
     econom
    -2.33
     Bloody
    -2.10
     benches
    -2.09
     Ernst
    -2.08
     Occupy
    -2.06
     improv
    -1.99
    eworks
    -1.99
    eur
    -1.99
     Civic
    -1.99
     Richards
    -1.98
    POSITIVE LOGITS
    send
    3.69
    Send
    3.63
     send
    3.54
     Send
    3.27
     sent
    3.16
    Sent
    3.14
    sent
    3.00
     Sent
    2.91
     sending
    2.79
     Sending
    2.77
    Activations Density 0.001%

    No Known Activations