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. 44395
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experiences and feelings related to identity

    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
    0:0.04
    1:0.02
    2:0.04
    3:0.08
    4:0.17
    5:0.04
    6:0.05
    7:0.09
    8:0.12
    9:0.08
    10:0.09
    11:0.13
    Negative Logits
    racuse
    -2.16
    duino
    -2.00
    Reviewer
    -1.94
    arak
    -1.92
    istries
    -1.80
    payers
    -1.78
    wm
    -1.72
    arthy
    -1.71
    orum
    -1.70
     alike
    -1.70
    POSITIVE LOGITS
     planned
    1.75
    """
    1.70
     Zy
    1.67
     Era
    1.66
     Zer
    1.61
     Coming
    1.60
     Franch
    1.58
    recated
    1.58
     Shea
    1.58
     disbanded
    1.55
    Activations Density 0.003%

    No Known Activations