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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 18925
    Prev
    Next
    INDEX
    Explanations

    descriptors and attributes of individuals, particularly in terms of their roles, professions, and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    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
    2:0.04
    3:0.23
    4:0.02
    5:0.08
    6:0.02
    7:0.09
    8:0.02
    9:0.01
    10:0.33
    11:0.04
    Negative Logits
    skirts
    -2.30
     leases
    -2.25
     expansions
    -2.22
     engagements
    -2.15
    gments
    -2.08
     suspensions
    -2.05
     plans
    -2.05
     vacations
    -2.03
     resolutions
    -1.99
     arrangements
    -1.99
    POSITIVE LOGITS
     capable
    2.59
     thinker
    2.34
     competent
    2.14
     breaker
    2.11
     worthy
    2.09
     regardless
    2.09
    araoh
    2.07
     defender
    2.06
     responsible
    2.06
     politician
    2.01
    Activations Density 0.428%

    No Known Activations