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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44270
    Prev
    Next
    INDEX
    Explanations

    references to actions taken by bystanders in various situations

    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
    1:0.01
    2:0.07
    3:0.07
    4:0.07
    5:0.03
    6:0.07
    7:0.18
    8:0.04
    9:0.04
    10:0.27
    11:0.08
    Negative Logits
     Gloss
    -1.53
     Schedule
    -1.46
    atisf
    -1.46
     dominating
    -1.44
    ortment
    -1.40
     formulations
    -1.37
    gran
    -1.36
    armac
    -1.35
     adul
    -1.35
     Manor
    -1.34
    POSITIVE LOGITS
     bystand
    1.99
     TTL
    1.62
     bystanders
    1.61
     torch
    1.56
    */(
    1.50
    gee
    1.47
    tif
    1.42
     takedown
    1.40
     filmmaking
    1.39
     responders
    1.39
    Activations Density 0.000%

    No Known Activations