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. 43534
    Prev
    Next
    INDEX
    Explanations

    structured data or bullet points that outline specific information

    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
    0:0.28
    1:0.08
    2:0.02
    3:0.04
    4:0.04
    5:0.05
    6:0.05
    7:0.01
    8:0.15
    9:0.08
    10:0.07
    11:0.06
    Negative Logits
    ETF
    -1.72
    ARC
    -1.64
    Champ
    -1.54
    GD
    -1.36
     Canaveral
    -1.32
    ASC
    -1.31
    Tube
    -1.31
     exha
    -1.30
    Storage
    -1.28
    Stud
    -1.28
    POSITIVE LOGITS
    nce
    1.64
    rity
    1.59
    opsis
    1.58
    �
    1.49
    uga
    1.49
    ibaba
    1.47
    iola
    1.45
    agy
    1.44
    ::
    1.42
    patrick
    1.40
    Activations Density 0.007%

    No Known Activations