© 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. 42293
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts between different entities or ideas

    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
    1:0.03
    2:0.10
    3:0.12
    4:0.28
    5:0.04
    6:0.05
    7:0.11
    8:0.05
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
     replaced
    -1.62
     forwarded
    -1.58
     accompanied
    -1.47
     capped
    -1.47
     promptly
    -1.45
     flanked
    -1.45
     jointly
    -1.45
     proceeded
    -1.41
     teamed
    -1.40
     coincided
    -1.38
    POSITIVE LOGITS
    norm
    1.74
     counterparts
    1.74
    normal
    1.73
     contemporaries
    1.66
    typ
    1.65
     norm
    1.65
    ecause
    1.55
    enne
    1.53
    other
    1.52
    usual
    1.52
    Activations Density 0.028%

    No Known Activations