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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 44097
    Prev
    Next
    INDEX
    Explanations

    adjectives describing characteristics or qualities of objects and situations

    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
    0:0.02
    1:0.02
    2:0.17
    3:0.07
    4:0.11
    5:0.03
    6:0.32
    7:0.07
    8:0.02
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
    gdala
    -1.38
     guiActiveUn
    -1.25
    uador
    -1.22
     Bans
    -1.19
    iquette
    -1.17
    TN
    -1.17
     association
    -1.16
    isha
    -1.16
    OUN
    -1.13
     Dragons
    -1.12
    POSITIVE LOGITS
    achy
    1.52
    sed
    1.52
     wiser
    1.46
    ministic
    1.41
     hassle
    1.38
    fficient
    1.37
    ught
    1.36
    ifiable
    1.35
    ivable
    1.31
    atur
    1.31
    Activations Density 0.025%

    No Known Activations