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. 9356
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their roles within the context of significant events or 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
    0:0.05
    1:0.05
    2:0.20
    3:0.03
    4:0.02
    5:0.03
    6:0.06
    7:0.02
    8:0.03
    9:0.03
    10:0.37
    11:0.05
    Negative Logits
     Rud
    -2.47
     Rebell
    -2.36
     fert
    -2.27
     Oss
    -2.26
     Od
    -2.17
    š
    -2.16
    :{
    -2.14
     Yugoslav
    -2.11
     Rudolph
    -2.09
     imagin
    -2.07
    POSITIVE LOGITS
    CA
    4.96
    ca
    3.99
     CA
    3.93
    Ca
    2.93
    CB
    2.69
    cs
    2.69
    CHA
    2.65
    CE
    2.64
    CI
    2.61
    cam
    2.55
    Activations Density 0.001%

    No Known Activations