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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 7362
    Prev
    Next
    INDEX
    Explanations

    words related to actions or states of being, particularly those that convey emotional or sensory qualities

    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
    1:0.02
    2:0.07
    3:0.04
    4:0.07
    5:0.04
    6:0.06
    7:0.29
    8:0.04
    9:0.04
    10:0.22
    11:0.04
    Negative Logits
    aido
    -2.12
    aucuses
    -2.03
     commute
    -2.01
     commuting
    -1.98
     coordinate
    -1.98
    unte
    -1.91
     volunte
    -1.87
    ilater
    -1.79
     consortium
    -1.79
     reunited
    -1.76
    POSITIVE LOGITS
     clich
    2.44
    inventoryQuantity
    2.39
     phrases
    2.29
     adject
    2.10
     Hits
    2.10
     warnings
    2.06
     insults
    2.04
     myths
    1.97
     aph
    1.94
     stale
    1.90
    Activations Density 0.000%

    No Known Activations