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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 3101
    Prev
    Next
    INDEX
    Explanations

    specific references to groups of people and actions related to accountability or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.02
    2:0.17
    3:0.12
    4:0.08
    5:0.05
    6:0.18
    7:0.03
    8:0.06
    9:0.09
    10:0.07
    11:0.05
    Negative Logits
     Polo
    -1.38
     Chase
    -1.30
     Catalyst
    -1.26
     [*
    -1.20
     Rockies
    -1.17
    ARP
    -1.15
     scanning
    -1.15
     Cros
    -1.14
     Haas
    -1.14
    ADRA
    -1.12
    POSITIVE LOGITS
    "]=>
    1.76
    basketball
    1.56
     sqor
    1.46
    BuyableInstoreAndOnline
    1.43
     david
    1.42
    usa
    1.38
     };
    1.38
    malink
    1.36
    english
    1.36
    andre
    1.32
    Activations Density 0.016%

    No Known Activations