© 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. 2-ATT-KK
    11. 22851
    Prev
    Next
    INDEX
    Explanations

    details or descriptions of specific events or situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to specific geographical locations and their populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.09
    3:0.07
    4:0.20
    5:0.05
    6:0.02
    7:0.08
    8:0.04
    9:0.12
    10:0.14
    11:0.08
    Negative Logits
    jew
    -1.16
    QL
    -1.13
     Lover
    -1.05
     QC
    -1.05
    arthed
    -1.02
     fusion
    -1.00
    balls
    -0.99
    eder
    -0.98
    atron
    -0.98
    isman
    -0.98
    POSITIVE LOGITS
     quo
    1.22
    ──
    1.20
     periphery
    1.16
    tops
    1.11
    iblings
    1.08
     detrim
    1.08
    uries
    1.07
    heastern
    1.06
     adolesc
    1.05
    hops
    1.05
    Activations Density 0.011%

    No Known Activations