INDEX

Explanations

phrases expressing a sense of excess or intensity

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

Following "too"

np_acts-logits-general · gemini-2.0-flash

not too [adjective]

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 fís

-0.41

baguna

-0.40

 estekak

-0.40

PHYSICAL

-0.39

MessageWindow

-0.39

 Wikimedijinoj

-0.38

 ineffective

-0.37

InitStruct

-0.37

 PHYSICAL

-0.37

♼

-0.36

POSITIVE LOGITS

 betweenstory

0.48

 useRouter

0.47

 hopefully

0.45

 initComponents

0.44

そこまで

0.44

CloseOperation

0.43

hopefully

0.42

 NSMutable

0.42

StoryboardSegue

0.41

 Hopefully

0.41

Activations Density 0.160%

phrases expressing a sense of excess or intensity

Following "too"

not too [adjective]

No Comments

No Known Activations