INDEX

Explanations

the word pair "may be" or "may not"

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Negative Logits

 character

-0.52

ները

-0.51

énario

-0.50

ModelAdmin

-0.49

do

-0.48

 бъдат

-0.48

のを

-0.48

DO

-0.47

CurrentValue

-0.47

 clearly

-0.46

POSITIVE LOGITS

 mắn

0.94

onnaise

0.85

may

0.84

MAY

0.83

May

0.83

MigrationBuilder

0.82

MAY

0.81

anskje

0.77

 Mays

0.76

may

0.75

Activations Density 0.335%

the word pair "may be" or "may not"

No Known Activations