© 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. 10-ATT-KK
    11. 14479
    Prev
    Next
    INDEX
    Explanations

    references to individuals' identities and the socio-political context surrounding them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.02
    2:0.06
    3:0.05
    4:0.07
    5:0.31
    6:0.02
    7:0.05
    8:0.02
    9:0.24
    10:0.01
    11:0.06
    Negative Logits
    interrupted
    -2.73
     continues
    -2.71
    inventoryQuantity
    -2.71
     deteriorated
    -2.58
     curfew
    -2.52
     deterior
    -2.50
     stalled
    -2.48
    ��
    -2.43
    rower
    -2.37
     resume
    -2.36
    POSITIVE LOGITS
     respectively
    3.14
    types
    2.71
     Males
    2.58
    who
    2.45
    folk
    2.37
     yourselves
    2.35
     Except
    2.34
    tics
    2.33
    *.
    2.31
    ians
    2.31
    Activations Density 0.502%

    No Known Activations