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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7163
    Prev
    Next
    INDEX
    Explanations

    items or phrases related to demographic shifts and challenges

    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
    2:0.20
    3:0.06
    4:0.16
    5:0.04
    6:0.10
    7:0.15
    8:0.03
    9:0.05
    10:0.05
    11:0.07
    Negative Logits
    CHAT
    -1.74
    onal
    -1.56
    archment
    -1.53
    ecd
    -1.51
    rosso
    -1.50
    veland
    -1.49
    ideon
    -1.48
    omever
    -1.47
    FORMATION
    -1.44
    intendent
    -1.44
    POSITIVE LOGITS
     altogether
    1.38
     spectrum
    1.38
     category
    1.33
    ー
    1.30
     heap
    1.30
     coma
    1.26
     bandwagon
    1.24
     lineup
    1.23
     beams
    1.21
     wagon
    1.21
    Activations Density 0.001%

    No Known Activations