INDEX

Explanations

positive superlative adjectives indicating quality

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

"Best" followed by various words

np_acts-logits-general · gemini-2.0-flash

best followed by superlatives

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

OGND

-0.77

WithIOException

-0.74

 AssemblyTitle

-0.72

 оригіналу

-0.71

ViewFeatures

-0.70

 getItemCount

-0.65

crumbs

-0.64

 فريبيس

-0.63

yntaxException

-0.63

ItemBackground

-0.63

POSITIVE LOGITS

 BEST

0.94

BEST

0.94

 Best

0.91

sellers

0.87

 suited

0.86

Best

0.82

best

0.82

 best

0.81

 practices

0.80

selling

0.78

Activations Density 0.068%

positive superlative adjectives indicating quality

"Best" followed by various words

best followed by superlatives

No Comments

No Known Activations