© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 18976
    Prev
    Next
    INDEX
    Explanations

    mentions of financial performance and impacts related to companies

    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
    1:0.01
    2:0.06
    3:0.08
    4:0.10
    5:0.10
    6:0.04
    7:0.36
    8:0.03
    9:0.03
    10:0.03
    11:0.03
    Negative Logits
    oeuv
    -2.61
    laughter
    -2.57
    estern
    -2.56
    �
    -2.55
    uese
    -2.55
    rious
    -2.52
    omial
    -2.51
    ossibility
    -2.48
    ilogy
    -2.43
    ifix
    -2.39
    POSITIVE LOGITS
     its
    6.56
     Its
    6.19
    Its
    5.40
     ITS
    4.57
     itself
    3.85
    its
    3.48
     subsidiary
    3.25
     subsidiaries
    3.03
     affiliates
    3.02
     customers
    2.58
    Activations Density 1.341%

    No Known Activations