INDEX

Explanations

lexical items related to vocabulary and language sophistication

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

grammar, words, and language

np_acts-logits-general · gemini-2.0-flash

language, words, vocabulary, spelling

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

__*/

-0.52

CloseOperation

-0.52

 оригіналу

-0.50

///</

-0.49

 defaultstate

-0.48

DockStyle

-0.47

complexContent

-0.47

NewRow

-0.46

}))

-0.45

getCmp

-0.45

POSITIVE LOGITS

 word

1.73

 words

1.69

 Words

1.46

 Word

1.41

 vocabulary

1.38

Word

1.37

Words

1.36

word

1.36

 spelling

1.35

 WORDS

1.33

Activations Density 0.613%

lexical items related to vocabulary and language sophistication

grammar, words, and language

language, words, vocabulary, spelling

No Comments

No Known Activations