© 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. 7871
    Prev
    Next
    INDEX
    Explanations

    references to various skills and abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    2:0.09
    3:0.05
    4:0.06
    5:0.04
    6:0.03
    7:0.06
    8:0.04
    9:0.05
    10:0.35
    11:0.13
    Negative Logits
     protesters
    -1.60
     airing
    -1.54
     broadcasts
    -1.50
     advertisements
    -1.43
    dule
    -1.42
    radio
    -1.42
     microphones
    -1.41
    atories
    -1.40
     adul
    -1.39
    nsic
    -1.37
    POSITIVE LOGITS
     skills
    2.23
    skill
    2.17
     skill
    2.15
     proficiency
    2.13
     Skills
    2.01
     Skill
    1.99
     innate
    1.98
     agility
    1.91
     mastery
    1.89
    Ability
    1.87
    Activations Density 0.295%

    No Known Activations