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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 43412
    Prev
    Next
    INDEX
    Explanations

    information about films, including their details like directors, writers, and cast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.01
    2:0.07
    3:0.11
    4:0.08
    5:0.06
    6:0.03
    7:0.07
    8:0.05
    9:0.10
    10:0.23
    11:0.10
    Negative Logits
     selfie
    -1.55
    kas
    -1.52
     EF
    -1.43
     Answers
    -1.41
     bios
    -1.41
    isphere
    -1.32
     �
    -1.32
     acron
    -1.31
     docs
    -1.30
     bullish
    -1.30
    POSITIVE LOGITS
     subsequent
    1.59
     Defendants
    1.48
     installments
    1.47
     pulp
    1.36
    quartered
    1.32
    ]-
    1.29
    1972
    1.28
    ).[
    1.28
    exclusive
    1.27
     illegitimate
    1.25
    Activations Density 0.012%

    No Known Activations