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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 7797
    Prev
    Next
    INDEX
    Explanations

    expressions of self-congratulation or self-praise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.03
    2:0.08
    3:0.15
    4:0.02
    5:0.03
    6:0.10
    7:0.11
    8:0.06
    9:0.17
    10:0.07
    11:0.11
    Negative Logits
     difficulty
    -1.10
     arrang
    -1.05
     repayment
    -1.02
     counsel
    -1.00
    ��
    -0.99
     Var
    -0.97
     Difficulty
    -0.96
     quantity
    -0.96
    etheless
    -0.96
     bouts
    -0.94
    POSITIVE LOGITS
    akura
    1.16
    ONY
    1.15
    llah
    1.14
    ylon
    1.12
     quo
    1.10
    ippi
    1.09
    orsi
    1.07
    Adams
    1.07
    Columb
    1.06
    anamo
    1.06
    Activations Density 0.002%

    No Known Activations