INDEX

Explanations

comparative phrases related to measurements or values

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

Greater than or less than symbols

np_acts-logits-general · gemini-2.0-flash

numerical comparisons and thresholds

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

-0.56

-0.53

-0.52

ีก

-0.52

’

-0.50

-0.44

 still

-0.43

Referències

-0.42

 toujours

-0.42

POSITIVE LOGITS

OrEqual

1.03

 THAN

0.94

 than

0.93

Than

0.92

 threshold

0.91

IntoConstraints

0.90

XMLSchema

0.90

ंदीखरीदारी

0.88

OrEqualTo

0.85

 thresholds

0.85

Activations Density 0.491%

comparative phrases related to measurements or values

Greater than or less than symbols

numerical comparisons and thresholds

No Comments

No Known Activations