© 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. 28813
    Prev
    Next
    INDEX
    Explanations

    statements related to research findings and their implications

    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
    2:0.08
    3:0.08
    4:0.09
    5:0.03
    6:0.06
    7:0.06
    8:0.05
    9:0.04
    10:0.29
    11:0.14
    Negative Logits
    aran
    -1.47
    uminati
    -1.29
     lobbying
    -1.21
    osphere
    -1.19
     eas
    -1.18
     protector
    -1.18
     imped
    -1.15
    perty
    -1.14
     Slave
    -1.14
     Monarch
    -1.14
    POSITIVE LOGITS
     reviewers
    1.70
    Results
    1.67
    Analysis
    1.64
     qualitative
    1.50
     Results
    1.45
     findings
    1.44
    rition
    1.43
    Discussion
    1.40
    RESULTS
    1.38
    undown
    1.37
    Activations Density 0.062%

    No Known Activations