© 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. 43265
    Prev
    Next
    INDEX
    Explanations

    punctuations and pauses in text

    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
    0:0.03
    1:0.01
    2:0.05
    3:0.05
    4:0.13
    5:0.03
    6:0.38
    7:0.04
    8:0.04
    9:0.07
    10:0.08
    11:0.04
    Negative Logits
     incl
    -1.34
    esters
    -1.29
     taxp
    -1.29
    tops
    -1.26
     lever
    -1.24
     Alexandria
    -1.20
    ————————
    -1.20
    [/
    -1.20
     Brune
    -1.20
    orship
    -1.19
    POSITIVE LOGITS
    properties
    1.55
     horizont
    1.52
    awaru
    1.46
    unin
    1.43
    MAL
    1.39
    itizen
    1.39
    ANA
    1.36
     Enhancement
    1.35
    angu
    1.28
    aviour
    1.28
    Activations Density 0.248%

    No Known Activations