Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 27367
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe qualities or characteristics

    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
    0:0.12
    1:0.01
    2:0.22
    3:0.06
    4:0.05
    5:0.03
    6:0.12
    7:0.04
    8:0.16
    9:0.04
    10:0.05
    11:0.04
    Negative Logits
    ATER
    -1.63
    BOOK
    -1.62
    ilaterally
    -1.58
    ocally
    -1.58
     bombed
    -1.53
    Liter
    -1.50
     EDITION
    -1.49
    idated
    -1.48
    icipated
    -1.47
    projects
    -1.45
    POSITIVE LOGITS
     Tsukuyomi
    1.45
     Gillespie
    1.41
     nonetheless
    1.41
     fa
    1.37
     accent
    1.37
     puzz
    1.36
     weigh
    1.34
     Duncan
    1.32
     abs
    1.31
     respectively
    1.30
    Activations Density 0.000%

    No Known Activations