© 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. 42613
    Prev
    Next
    INDEX
    Explanations

    references to accusations or claims regarding individuals or 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
    0:0.02
    1:0.01
    2:0.04
    3:0.14
    4:0.33
    5:0.04
    6:0.02
    7:0.10
    8:0.05
    9:0.05
    10:0.07
    11:0.07
    Negative Logits
     largeDownload
    -1.53
     quot
    -1.42
    multipl
    -1.41
    *.
    -1.41
    方
    -1.40
    artifacts
    -1.40
     invis
    -1.38
     attest
    -1.37
     migr
    -1.33
     ILCS
    -1.31
    POSITIVE LOGITS
     superiors
    1.80
    erity
    1.75
     authorities
    1.74
    orians
    1.68
     inaction
    1.67
     agencies
    1.65
    users
    1.65
     employers
    1.59
     regulators
    1.59
    ackers
    1.57
    Activations Density 0.024%

    No Known Activations