© 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. 3257
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'L' and its variations or accents

    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
    0:0.03
    1:0.07
    2:0.02
    3:0.06
    4:0.14
    5:0.05
    6:0.13
    7:0.06
    8:0.04
    9:0.05
    10:0.18
    11:0.10
    Negative Logits
    ahime
    -2.93
    ubes
    -2.74
    obos
    -2.59
     torpedo
    -2.44
    uba
    -2.44
    yne
    -2.42
     experien
    -2.27
    iatus
    -2.27
     sail
    -2.26
    uese
    -2.25
    POSITIVE LOGITS
    �
    5.33
     �
    5.29
    �
    3.94
    ■
    3.84
    ‎
    3.00
    ►
    2.97
    『
    2.95
    †
    2.94
    ¶
    2.89
     ¶
    2.83
    Activations Density 0.173%

    No Known Activations