INDEX

Explanations

grammatical terminology related to verbs and their modifiers

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

preceding a verb or noun

np_acts-logits-general · gemini-2.0-flash

grammatical categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 ostavi

-0.59

)))));

-0.56

 виправивши

-0.53

TestingModule

-0.52

IndentedString

-0.48

 NSCoder

-0.48

MockMvc

-0.47

}{\

-0.47

])){

-0.47

sizeCache

-0.45

POSITIVE LOGITS

 verbs

0.84

 preposition

0.81

 nouns

0.80

 noun

0.78

 verb

0.77

 adjectives

0.74

 adjective

0.71

 adverbs

0.70

 adverb

0.68

verb

0.66

Activations Density 0.242%

grammatical terminology related to verbs and their modifiers

preceding a verb or noun

grammatical categories

No Comments

No Known Activations