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. 44365
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals, particularly prominent figures or authorities

    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
    0:0.08
    1:0.08
    2:0.08
    3:0.08
    4:0.07
    5:0.08
    6:0.08
    7:0.08
    8:0.09
    9:0.06
    10:0.09
    11:0.09
    Negative Logits
     Pastebin
    -1.67
     folder
    -1.65
     tweet
    -1.59
     archive
    -1.56
     username
    -1.54
     guid
    -1.50
     retina
    -1.48
     tid
    -1.47
     archived
    -1.46
     github
    -1.44
    POSITIVE LOGITS
    ccording
    1.83
    ��
    1.80
    ��極
    1.76
    hered
    1.72
    20439
    1.70
    �
    1.68
    illery
    1.62
    omorph
    1.61
     estab
    1.60
    429
    1.58
    Activations Density 0.000%

    No Known Activations