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. 9-ATT-KK
    6. 18602
    Prev
    Next
    INDEX
    Explanations

    expressions indicating opinions or subjective statements

    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
    1:0.08
    2:0.08
    3:0.08
    4:0.08
    5:0.07
    6:0.08
    7:0.09
    8:0.08
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
    anyahu
    -3.38
    aber
    -3.10
    vari
    -3.04
    actionDate
    -2.85
    zac
    -2.83
    ��
    -2.79
    aq
    -2.69
    CONCLUS
    -2.64
    GY
    -2.62
    gran
    -2.59
    POSITIVE LOGITS
    ··
    2.83
     takedown
    2.78
    Ru
    2.57
     setbacks
    2.49
     Hirosh
    2.49
     Trash
    2.48
     Britt
    2.45
     messy
    2.45
     Hue
    2.42
    Tree
    2.37
    Activations Density 0.000%

    No Known Activations