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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 43354
    Prev
    Next
    INDEX
    Explanations

    occurrences of high numbers, specifically related to significant achievements or events

    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
    0:0.03
    1:0.02
    2:0.06
    3:0.14
    4:0.07
    5:0.06
    6:0.18
    7:0.04
    8:0.07
    9:0.12
    10:0.10
    11:0.06
    Negative Logits
     foremost
    -1.19
     hereafter
    -1.00
    marked
    -0.99
     soon
    -0.93
     intermedi
    -0.86
     rece
    -0.85
     incorpor
    -0.84
     thereafter
    -0.82
    cture
    -0.81
     Mellon
    -0.81
    POSITIVE LOGITS
     Expand
    1.13
    inosaur
    1.05
    ioxid
    1.02
    gress
    1.01
    itamin
    0.97
    Untitled
    0.96
     Catalog
    0.95
     Allaah
    0.94
    orneys
    0.93
    Arcade
    0.93
    Activations Density 0.194%

    No Known Activations