© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 45535
    Prev
    Next
    INDEX
    Explanations

    references to physical features and attributes of individuals, particularly their heads and faces

    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
    0:0.04
    1:0.02
    2:0.20
    3:0.11
    4:0.15
    5:0.06
    6:0.05
    7:0.09
    8:0.04
    9:0.04
    10:0.06
    11:0.08
    Negative Logits
     pilgr
    -1.52
     devote
    -1.44
     Incarn
    -1.42
     reconc
    -1.37
    ocious
    -1.33
     CHRIST
    -1.31
    atever
    -1.30
    "!
    -1.29
     reinforcements
    -1.27
     arrang
    -1.25
    POSITIVE LOGITS
     depends
    1.56
     varies
    1.47
     depended
    1.45
     extends
    1.41
    acted
    1.35
     differs
    1.33
    ifies
    1.31
     contains
    1.29
     differed
    1.29
     relies
    1.28
    Activations Density 0.058%

    No Known Activations