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. 3-ATT-KK
    6. 8380
    Prev
    Next
    INDEX
    Explanations

    references to processes and actions related to selection and control mechanisms

    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
    0:0.05
    1:0.04
    2:0.08
    3:0.03
    4:0.06
    5:0.06
    6:0.12
    7:0.31
    8:0.05
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
     careers
    -1.10
     feud
    -1.08
     majorities
    -1.05
     Entered
    -1.05
     Journalists
    -1.04
    catentry
    -1.03
    antine
    -1.03
     portfolios
    -1.02
     Pension
    -1.01
     accuses
    -1.00
    POSITIVE LOGITS
     itself
    1.80
    ertodd
    1.28
    alone
    1.25
    verty
    1.16
    tyard
    1.07
    itiz
    1.06
     its
    1.05
    imming
    1.05
    irlf
    1.04
    hang
    1.03
    Activations Density 0.679%

    No Known Activations