© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22756
    Prev
    Next
    INDEX
    Explanations

    cognitive and behavioral topics related to cognitive abilities, cognitive performance, cognitive behavior, and cognitive demands

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

    terms related to cognitive abilities and performance

    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
    0:0.05
    1:0.04
    2:0.24
    3:0.08
    4:0.13
    5:0.04
    6:0.02
    7:0.04
    8:0.03
    9:0.20
    10:0.06
    11:0.03
    Negative Logits
    yip
    -1.49
    olicited
    -1.34
    ento
    -1.27
    KK
    -1.26
     Wanted
    -1.25
     seams
    -1.23
    ouk
    -1.22
    xxxxxxxx
    -1.20
    nen
    -1.19
    NY
    -1.17
    POSITIVE LOGITS
    etics
    1.40
     pathways
    1.35
    VICE
    1.32
    advertisement
    1.30
     sclerosis
    1.28
    urally
    1.28
    SPONSORED
    1.28
     prog
    1.24
     medicine
    1.20
     ALS
    1.18
    Activations Density 0.011%

    No Known Activations