INDEX

Explanations

expressions of gratitude

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

Appreciation or gratitude ("thanks in advance")

np_acts-logits-general · gemini-2.0-flash

thanks in advance

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

ⓧ

-0.81

DrawerLayout

-0.70

SourceChecksum

-0.68

ScopeManager

-0.59

ArgsConstructor

-0.59

TagMode

-0.56

клопе

-0.53

 snippetHide

-0.52

 onOptions

-0.51

ResponseWriter

-0.51

POSITIVE LOGITS

 advance

2.44

 ahead

2.31

 beforehand

2.19

advance

2.05

 AHEAD

1.98

 Advance

1.97

ahead

1.97

 Ahead

1.96

Advance

1.90

Ahead

1.86

Activations Density 0.368%

expressions of gratitude

Appreciation or gratitude ("thanks in advance")

thanks in advance

No Comments

No Known Activations