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. 9-ATT-KK
    6. 10699
    Prev
    Next
    INDEX
    Explanations

    parenthetical statements and content related to personal beliefs or commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.04
    2:0.05
    3:0.06
    4:0.06
    5:0.05
    6:0.12
    7:0.06
    8:0.05
    9:0.29
    10:0.05
    11:0.07
    Negative Logits
     Phillips
    -4.03
    olson
    -3.59
     Caldwell
    -3.54
     Inquisition
    -3.44
     Flores
    -3.31
     Williamson
    -3.20
     Cullen
    -3.17
     Kl
    -3.15
     forg
    -3.15
     Wade
    -3.13
    POSITIVE LOGITS
    Bernie
    6.19
     Bernie
    5.89
    actionDate
    4.25
     Freddie
    3.39
    annie
    3.37
    Bug
    3.35
    MON
    3.31
     Babe
    3.29
    ū
    3.21
    е
    3.17
    Activations Density 0.001%

    No Known Activations