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. 7202
    Prev
    Next
    INDEX
    Explanations

    instances of deception and exaggeration in statements or claims

    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
    0:0.02
    1:0.01
    2:0.10
    3:0.10
    4:0.06
    5:0.05
    6:0.02
    7:0.06
    8:0.07
    9:0.07
    10:0.21
    11:0.18
    Negative Logits
    aughters
    -1.22
    enery
    -1.16
     Surv
    -1.13
    cellaneous
    -1.08
    agara
    -1.06
    athlon
    -1.05
    trak
    -1.04
    hei
    -1.02
     Ascend
    -1.02
    achusetts
    -1.02
    POSITIVE LOGITS
     baseless
    1.55
     discredited
    1.50
     bogus
    1.35
     flawed
    1.35
     misguided
    1.33
     straw
    1.33
     nonexistent
    1.32
     discredit
    1.30
     phony
    1.30
     scapego
    1.28
    Activations Density 1.658%

    No Known Activations