© 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 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. 3282
    Prev
    Next
    INDEX
    Explanations

    narratives focused on personal journeys and relationships

    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
    2:0.11
    3:0.20
    4:0.23
    5:0.03
    6:0.02
    7:0.07
    8:0.03
    9:0.03
    10:0.10
    11:0.08
    Negative Logits
    ��極
    -2.07
    7601
    -1.72
    Reviewed
    -1.71
    Asset
    -1.70
    Num
    -1.67
    erker
    -1.66
    Ins
    -1.63
     Mastery
    -1.59
     References
    -1.58
    alling
    -1.57
    POSITIVE LOGITS
     discrete
    1.75
     incarcerated
    1.66
     eccentric
    1.62
     Judah
    1.61
     shuff
    1.61
     ferment
    1.57
     passively
    1.57
     submerged
    1.56
     lawfully
    1.56
     striving
    1.55
    Activations Density 0.009%

    No Known Activations