INDEX

Explanations

variations of the word "express" and related terms indicating expression or representation

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

"Express" and variants

np_acts-logits-general · gemini-2.0-flash

expressing formulas and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

WindowConstants

-0.65

assertEqual

-0.56

ɒ

-0.55

CloseOperation

-0.53

penters

-0.52

 HttpServlet

-0.52

زيز

-0.51

pernicus

-0.51

 ddelweddau

-0.50

UnknownFieldSet

-0.50

POSITIVE LOGITS

ément

0.84

 EXPRESS

0.83

 expressions

0.80

EXPRESS

0.76

 Expressions

0.75

Expressions

0.73

 condolences

0.73

 expr

0.72

expressions

0.70

Express

0.67

Activations Density 0.089%

variations of the word "express" and related terms indicating expression or representation

"Express" and variants

expressing formulas and concepts

No Comments

No Known Activations