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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22131
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the effects of various issues or phenomena

    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
    0:0.04
    1:0.02
    2:0.15
    3:0.04
    4:0.28
    5:0.07
    6:0.02
    7:0.02
    8:0.12
    9:0.14
    10:0.04
    11:0.01
    Negative Logits
    WithNo
    -1.41
    �
    -1.35
     willing
    -1.30
    NAS
    -1.26
    Jess
    -1.26
    č
    -1.25
    enture
    -1.24
    Cour
    -1.23
    ��
    -1.21
    ISO
    -1.21
    POSITIVE LOGITS
    ratom
    1.61
    hops
    1.47
    effects
    1.43
     exacerbate
    1.42
     impacts
    1.40
     worsen
    1.33
     pollutants
    1.31
     harm
    1.30
     adversely
    1.27
     destabil
    1.26
    Activations Density 0.007%

    No Known Activations