INDEX

Explanations

occurrences of the chemical symbol "Te" and related terms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"Te" followed by another character/token

np_acts-logits-general · gemini-2.0-flash

Te/te prefix

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

évaluateur

-0.76

Izvori

-0.74

 fluence

-0.69

 Վերցված

-0.68

CreateModel

-0.68

الإنجليزية

-0.66

 ब्रेकडाउन

-0.66

getExternal

-0.65

 Imit

-0.64

Sklici

-0.64

POSITIVE LOGITS

Te

0.73

Te

0.62

 Teas

0.56

te

0.52

Teo

0.51

 teki

0.49

+};

0.48

 tarik

0.47

Teh

0.47

 сказать

0.46

Activations Density 0.092%

occurrences of the chemical symbol "Te" and related terms

"Te" followed by another character/token

Te/te prefix

No Comments

No Known Activations