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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 20548
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial assistance and its implications

    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
    0:0.04
    1:0.02
    2:0.06
    3:0.18
    4:0.01
    5:0.05
    6:0.01
    7:0.04
    8:0.02
    9:0.01
    10:0.47
    11:0.03
    Negative Logits
    etta
    -2.25
    assador
    -2.20
    ioch
    -2.12
    ieft
    -2.07
     Lift
    -2.06
    odiac
    -2.06
     congratulations
    -2.01
    erning
    -1.97
    knit
    -1.97
     congratulated
    -1.94
    POSITIVE LOGITS
     wrong
    4.59
     incorrectly
    4.59
     incomplete
    4.43
     poorly
    4.40
     incorrect
    4.37
     unsu
    4.34
     ineffective
    4.29
     inefficient
    4.25
     inadequate
    4.20
     inconsist
    4.17
    Activations Density 1.975%

    No Known Activations