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. 43363
    Prev
    Next
    INDEX
    Explanations

    statements or comments related to education and government decisions

    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
    0:0.05
    1:0.02
    2:0.27
    3:0.17
    4:0.03
    5:0.04
    6:0.02
    7:0.03
    8:0.04
    9:0.07
    10:0.09
    11:0.10
    Negative Logits
     hereafter
    -1.29
    ?),
    -1.26
     Dynam
    -1.21
     Dungeons
    -1.19
     manifest
    -1.18
     Person
    -1.17
     dear
    -1.16
     singular
    -1.13
     selves
    -1.13
     Manifest
    -1.11
    POSITIVE LOGITS
    angan
    1.49
    inion
    1.47
    guyen
    1.41
    verett
    1.41
     Flavoring
    1.38
    yright
    1.38
    bda
    1.37
    isky
    1.36
    ews
    1.34
    iew
    1.34
    Activations Density 0.245%

    No Known Activations