© 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. 27649
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    2:0.10
    3:0.10
    4:0.06
    5:0.03
    6:0.15
    7:0.17
    8:0.08
    9:0.06
    10:0.10
    11:0.07
    Negative Logits
     Provided
    -1.70
     Provides
    -1.61
    antine
    -1.58
     Contains
    -1.54
     │
    -1.53
     ensures
    -1.45
    Alpha
    -1.45
     proves
    -1.41
     PROV
    -1.40
     consists
    -1.39
    POSITIVE LOGITS
    thood
    1.71
    die
    1.63
    athing
    1.59
     itch
    1.55
    mire
    1.54
    joice
    1.53
     weep
    1.50
    react
    1.49
     splash
    1.43
     admire
    1.42
    Activations Density 0.001%

    No Known Activations