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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 18971
    Prev
    Next
    INDEX
    Explanations

    elements of programming or technical discussions

    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
    1:0.06
    2:0.02
    3:0.12
    4:0.18
    5:0.18
    6:0.08
    7:0.05
    8:0.07
    9:0.05
    10:0.04
    11:0.06
    Negative Logits
    eatures
    -2.20
    anqu
    -2.16
    istar
    -2.12
     pione
    -2.11
    olo
    -2.08
    lio
    -2.02
    sted
    -2.01
    ascus
    -1.96
    uggest
    -1.94
    unda
    -1.93
    POSITIVE LOGITS
     Suppose
    3.61
     THEN
    2.62
     Wouldn
    2.53
     Surely
    2.45
     Assuming
    2.42
     hypot
    2.27
     suppose
    2.27
     preferably
    2.21
     then
    2.16
     suddenly
    2.14
    Activations Density 0.010%

    No Known Activations