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

    Neuronpedia

    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. 43910
    Prev
    Next
    INDEX
    Explanations

    words associated with gradients and measurements of performance or risk

    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
    0:0.07
    1:0.14
    2:0.04
    3:0.05
    4:0.04
    5:0.27
    6:0.05
    7:0.03
    8:0.05
    9:0.10
    10:0.07
    11:0.04
    Negative Logits
     nomination
    -1.44
     Born
    -1.36
     allegiance
    -1.34
     affiliation
    -1.33
     UD
    -1.32
     appearance
    -1.31
     Preferred
    -1.31
     endors
    -1.30
    reve
    -1.29
    ndra
    -1.29
    POSITIVE LOGITS
    WARE
    1.64
    ipel
    1.60
    ゴ
    1.59
    Balt
    1.56
    PLIED
    1.49
     istg
    1.44
     Grimoire
    1.40
     pandemonium
    1.37
    ograp
    1.37
     sqor
    1.36
    Activations Density 0.014%

    No Known Activations