© 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. 5-ATT-KK
    11. 43286
    Prev
    Next
    INDEX
    Explanations

    specific names or terms associated with notable figures or events in sports and entertainment

    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
    0:0.02
    1:0.03
    2:0.05
    3:0.04
    4:0.03
    5:0.04
    6:0.53
    7:0.05
    8:0.03
    9:0.05
    10:0.05
    11:0.04
    Negative Logits
    displayText
    -1.44
    STD
    -1.36
    abase
    -1.25
     variance
    -1.25
     defect
    -1.24
    channelAvailability
    -1.23
     trillions
    -1.20
     predicting
    -1.19
     binge
    -1.18
     propensity
    -1.15
    POSITIVE LOGITS
    asma
    1.58
    merce
    1.44
    nova
    1.43
    rencies
    1.38
    unic
    1.37
    monary
    1.37
     Lines
    1.30
    ondo
    1.30
    umat
    1.30
    ilon
    1.26
    Activations Density 0.143%

    No Known Activations