INDEX

Explanations

phrases that involve comparisons, particularly with numerical data

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

"Compared to"

np_acts-logits-general · gemini-2.0-flash

phrases of comparison

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 dalamnya

-0.49

ք

-0.47

sous

-0.45

ساء

-0.42

 thủ

-0.42

aksanaan

-0.41

：</

-0.41

Atsauces

-0.41

keley

-0.41

{(-

-0.40

POSITIVE LOGITS

IsContent

0.84

Datuak

0.79

 Référence

0.65

providedIn

0.64

SourceChecksum

0.62

interopRequire

0.61

 previously

0.61

 nothingness

0.60

 समीक्षाओं

0.60

ButterKnife

0.59

Activations Density 0.206%

phrases that involve comparisons, particularly with numerical data

"Compared to"

phrases of comparison

No Comments

No Known Activations