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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22266
    Prev
    Next
    INDEX
    Explanations

    commands related to database operations in a structured query language context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.04
    2:0.08
    3:0.08
    4:0.03
    5:0.07
    6:0.09
    7:0.06
    8:0.12
    9:0.11
    10:0.12
    11:0.05
    Negative Logits
    etheless
    -1.44
     horizont
    -1.31
    theless
    -1.25
    accompan
    -1.21
    �
    -1.18
     sugg
    -1.16
    udos
    -1.15
    jong
    -1.14
    conom
    -1.13
    yout
    -1.13
    POSITIVE LOGITS
    )/
    1.17
     decimal
    1.08
     );
    1.05
    oded
    1.01
     )
    1.00
     ):
    0.96
     unspecified
    0.96
    )-
    0.95
     1000
    0.89
     ballot
    0.88
    Activations Density 0.002%

    No Known Activations