© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 44794
    Prev
    Next
    INDEX
    Explanations

    language associated with formal requests and inquiries

    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
    0:0.02
    1:0.01
    2:0.13
    3:0.17
    4:0.08
    5:0.07
    6:0.01
    7:0.04
    8:0.07
    9:0.12
    10:0.14
    11:0.10
    Negative Logits
     tended
    -1.37
     Rivals
    -1.26
     exacerbated
    -1.23
     clustered
    -1.22
     accounted
    -1.21
     clusters
    -1.20
    toggle
    -1.17
     blamed
    -1.17
     routers
    -1.13
     exacerb
    -1.12
    POSITIVE LOGITS
     ______
    1.78
    morrow
    1.70
     tomorrow
    1.69
     ASAP
    1.61
     hereafter
    1.58
    ______
    1.43
     yourselves
    1.42
    ________
    1.40
    !!!!!
    1.40
    HCR
    1.40
    Activations Density 0.736%

    No Known Activations