INDEX

Explanations

phrases or concepts surrounding general assessment or evaluation

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

"All" followed by an adjective or adverb

np_acts-logits-general · gemini-2.0-flash

all followed by descriptive word

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

 всех

-0.63

 storici

-0.56

 všech

-0.54

"]);

-0.54

 wszystkich

-0.53

all

-0.51

 всей

-0.51

 всеми

-0.50

時には

-0.50

 каждую

-0.48

POSITIVE LOGITS

MLLoader

1.03

 disambiguazione

0.87

 defaultstate

0.79

parsedMessage

0.74

adaptiveStyles

0.73

 createContext

0.70

 bezeichneter

0.69

 CURIAM

0.69

הערות

0.68

writeField

0.64

Activations Density 0.088%

phrases or concepts surrounding general assessment or evaluation

"All" followed by an adjective or adverb

all followed by descriptive word

No Comments

No Known Activations