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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 20622
    Prev
    Next
    INDEX
    Explanations

    statements related to significant societal or moral issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.05
    2:0.06
    3:0.05
    4:0.34
    5:0.08
    6:0.05
    7:0.07
    8:0.05
    9:0.05
    10:0.04
    11:0.05
    Negative Logits
    othes
    -2.60
    ÍÍ
    -2.58
     Leilan
    -2.53
    BILITIES
    -2.49
    EFF
    -2.47
     AMER
    -2.45
     nerv
    -2.43
    ['
    -2.42
     THESE
    -2.33
     ORIG
    -2.33
    POSITIVE LOGITS
     Posted
    2.88
    Click
    2.79
     Click
    2.77
    Posted
    2.68
     Quote
    2.41
     Boll
    2.38
    arde
    2.37
     Speaker
    2.36
    Quote
    2.33
     Write
    2.31
    Activations Density 0.004%

    No Known Activations