© 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. 43428
    Prev
    Next
    INDEX
    Explanations

    grades and evaluations related to performance metrics

    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
    0:0.02
    1:0.02
    2:0.06
    3:0.05
    4:0.08
    5:0.01
    6:0.06
    7:0.37
    8:0.02
    9:0.03
    10:0.18
    11:0.06
    Negative Logits
    roots
    -1.63
    vag
    -1.57
    hots
    -1.55
    forth
    -1.54
    メ
    -1.52
    fold
    -1.48
    requ
    -1.46
    ibus
    -1.45
    sharing
    -1.45
    mone
    -1.45
    POSITIVE LOGITS
     grades
    2.09
    Grade
    1.98
     evaluations
    1.85
     evaluation
    1.81
     evaluating
    1.75
    erate
    1.73
     Ratings
    1.72
     Classification
    1.72
     outlook
    1.68
     graded
    1.68
    Activations Density 0.008%

    No Known Activations