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. 44211
    Prev
    Next
    INDEX
    Explanations

    phrases related to absence or failure to show up

    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
    0:0.01
    1:0.01
    2:0.12
    3:0.12
    4:0.16
    5:0.04
    6:0.03
    7:0.20
    8:0.05
    9:0.06
    10:0.08
    11:0.07
    Negative Logits
    hedon
    -1.40
    cellence
    -1.37
     irresistible
    -1.36
    rather
    -1.35
    ensional
    -1.26
    oso
    -1.25
    idis
    -1.24
    verty
    -1.23
    stellar
    -1.21
    DragonMagazine
    -1.21
    POSITIVE LOGITS
     anymore
    2.99
     nor
    2.33
    nor
    1.46
     :(
    1.38
     whatsoever
    1.38
     Nor
    1.37
     yet
    1.35
    yet
    1.32
     due
    1.32
     unless
    1.25
    Activations Density 0.288%

    No Known Activations