© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 19041
    Prev
    Next
    INDEX
    Explanations

    digital content related to "First Post" on social media or news platforms

    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
    0:0.03
    1:0.03
    2:0.04
    3:0.15
    4:0.15
    5:0.08
    6:0.04
    7:0.06
    8:0.04
    9:0.08
    10:0.13
    11:0.13
    Negative Logits
     implication
    -1.54
    issance
    -1.47
     consequ
    -1.44
     ranc
    -1.40
     flashbacks
    -1.37
    notations
    -1.35
     listeners
    -1.34
    ificantly
    -1.33
    uable
    -1.33
     libertarians
    -1.33
    POSITIVE LOGITS
     Acc
    1.59
     Featured
    1.52
     instr
    1.46
     Customs
    1.35
     homepage
    1.33
     inh
    1.30
     Sector
    1.29
     "\
    1.26
     Genius
    1.26
     Ascension
    1.25
    Activations Density 0.001%

    No Known Activations