© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22889
    Prev
    Next
    INDEX
    Explanations

    information related to political activities and news data, with some focus on names and locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    acronyms and abbreviations related to organizations or entities

    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
    0:0.08
    1:0.03
    2:0.28
    3:0.09
    4:0.11
    5:0.07
    6:0.03
    7:0.03
    8:0.08
    9:0.08
    10:0.05
    11:0.03
    Negative Logits
    Synopsis
    -1.31
    slice
    -1.22
    Anonymous
    -1.20
    CVE
    -1.15
    Gro
    -1.15
     spoilers
    -1.12
    yip
    -1.08
     Kov
    -1.08
     millisec
    -1.07
     Feast
    -1.05
    POSITIVE LOGITS
    monary
    1.59
    rency
    1.42
    iard
    1.38
    bid
    1.37
    heid
    1.33
     veins
    1.29
    atorial
    1.26
     resin
    1.23
    rences
    1.16
    ortium
    1.16
    Activations Density 0.006%

    No Known Activations