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. 7224
    Prev
    Next
    INDEX
    Explanations

    transitions indicating the flow of time in a narrative

    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
    0:0.05
    1:0.02
    2:0.05
    3:0.12
    4:0.13
    5:0.03
    6:0.07
    7:0.19
    8:0.03
    9:0.06
    10:0.10
    11:0.10
    Negative Logits
     mistaken
    -1.34
     enthusi
    -1.34
     affiliation
    -1.33
     originate
    -1.31
    ワン
    -1.31
     technique
    -1.27
     pseudonym
    -1.26
    soType
    -1.26
     motto
    -1.25
     specialization
    -1.24
    POSITIVE LOGITS
     Progress
    1.50
    rollers
    1.46
    progress
    1.41
    ogs
    1.38
     meanwhile
    1.36
    anwhile
    1.35
    Others
    1.32
     Others
    1.29
    ui
    1.27
    Scroll
    1.24
    Activations Density 0.011%

    No Known Activations