INDEX

Explanations

phrases related to requests and submissions for evaluations or decisions

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

Prepositions followed by nouns or pronouns

np_acts-logits-general · gemini-2.0-flash

purpose or recipient of action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

تقاوى

-0.63

 feroit

-0.59

 Monfieur

-0.57

 мәкал

-0.56

 avoient

-0.54

)++;

-0.54

writeField

-0.52

 auroit

-0.52

 ویکی‌پدی

-0.52

 ainfi

-0.52

POSITIVE LOGITS

HomeAsUp

0.38

UnknownFieldSet

0.38

 spec

0.36

phosa

0.35

 inspection

0.35

CppCodeGen

0.35

 display

0.34

La

0.33

„

0.33

display

0.33

Activations Density 0.240%

phrases related to requests and submissions for evaluations or decisions

Prepositions followed by nouns or pronouns

purpose or recipient of action

No Comments

No Known Activations