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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 35690
    Prev
    Next
    INDEX
    Explanations

    sections denoted by bullet points or markers

    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
    1:0.02
    2:0.15
    3:0.03
    4:0.04
    5:0.08
    6:0.19
    7:0.01
    8:0.13
    9:0.05
    10:0.03
    11:0.19
    Negative Logits
    claw
    -1.60
    Mouse
    -1.51
    eln
    -1.51
    gob
    -1.51
    deen
    -1.48
    LIN
    -1.47
    mpeg
    -1.47
    hyde
    -1.45
    Lens
    -1.45
    death
    -1.45
    POSITIVE LOGITS
     millenn
    1.46
     Pepsi
    1.36
    Champ
    1.36
     Chomsky
    1.36
    版
    1.35
     notor
    1.35
     Podesta
    1.34
     Atkinson
    1.33
     verse
    1.31
     Proposition
    1.30
    Activations Density 0.000%

    No Known Activations