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. 7-ATT-KK
    6. 9308
    Prev
    Next
    INDEX
    Explanations

    names of individuals and references to their roles or contributions

    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
    0:0.16
    1:0.02
    2:0.01
    3:0.03
    4:0.16
    5:0.06
    6:0.06
    7:0.12
    8:0.07
    9:0.06
    10:0.01
    11:0.19
    Negative Logits
     namely
    -1.99
     accordingly
    -1.79
    ◼
    -1.76
     kidding
    -1.75
     sensibilities
    -1.72
     louder
    -1.72
     momentarily
    -1.70
    ?!"
    -1.68
    !?"
    -1.67
     greatness
    -1.64
    POSITIVE LOGITS
    ullivan
    3.06
    verett
    2.58
     Lima
    2.19
    xon
    2.18
    tein
    2.14
    sted
    2.12
    orio
    2.11
    yne
    2.10
    herty
    2.08
    OHN
    2.07
    Activations Density 0.003%

    No Known Activations