© 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. 41871
    Prev
    Next
    INDEX
    Explanations

    taxonomy-related terms for scientific classification of biological entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.02
    2:0.09
    3:0.08
    4:0.07
    5:0.05
    6:0.03
    7:0.29
    8:0.05
    9:0.05
    10:0.10
    11:0.09
    Negative Logits
     readiness
    -1.66
     inaction
    -1.53
     deteriorating
    -1.50
     rever
    -1.48
     minimized
    -1.42
     wiping
    -1.41
     negatively
    -1.41
     incurred
    -1.39
     renovations
    -1.39
     closing
    -1.38
    POSITIVE LOGITS
    aceae
    1.75
    tera
    1.52
    anguages
    1.49
    idae
    1.49
     Narc
    1.47
    ��
    1.47
    arus
    1.46
    龍�
    1.46
    lance
    1.45
    acea
    1.42
    Activations Density 0.003%

    No Known Activations