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

    Neuronpedia

    Jacobian LensNEW
    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. 1440
    Prev
    Next
    INDEX
    Explanations

    phrases related to the decision-making process and goals in contexts such as budgeting and resource allocation

    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
    1:0.02
    2:0.06
    3:0.25
    4:0.06
    5:0.11
    6:0.04
    7:0.09
    8:0.07
    9:0.03
    10:0.08
    11:0.06
    Negative Logits
     ­
    -1.98
    �
    -1.77
    ­
    -1.73
    –
    -1.71
     I
    -1.70
    adj
    -1.67
     Presidency
    -1.63
     Brah
    -1.61
    �
    -1.60
     me
    -1.59
    POSITIVE LOGITS
     ourselves
    2.49
    senal
    2.03
    assadors
    1.90
    ostics
    1.88
    Submit
    1.87
    osponsors
    1.86
     caches
    1.83
    orks
    1.83
     Customers
    1.83
    paces
    1.82
    Activations Density 0.474%

    No Known Activations