INDEX

Explanations

phrases indicating a wide scope or variety of something

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

"Wide" followed by words indicating variety or range

np_acts-logits-general · gemini-2.0-flash

wide breadth

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

yntaxException

-0.79

RegressionTest

-0.78

 ModelExpression

-0.74

queryInterface

-0.73

CastException

-0.72

providedIn

-0.70

PRNewswire

-0.70

ronpa

-0.70

IndentedString

-0.69

HostException

-0.69

POSITIVE LOGITS

 range

0.89

 ranging

0.88

 array

0.81

awake

0.80

 variety

0.76

 spectrum

0.75

 awake

0.75

ranging

0.73

 scope

0.73

 spread

0.67

Activations Density 0.078%

phrases indicating a wide scope or variety of something

"Wide" followed by words indicating variety or range

wide breadth

No Comments

No Known Activations