INDEX

Explanations

references to time durations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 financières

-0.56

CrossRef

-0.56

vací

-0.53

 sanitaires

-0.53

gewöhn

-0.53

elding

-0.52

च्छ

-0.51

makeText

-0.50

PickerController

-0.47

GeneratedValue

-0.47

POSITIVE LOGITS

 hour

3.12

 hours

3.01

hour

2.99

 Hour

2.67

 HOUR

2.60

Hour

2.59

hours

2.55

 Hours

2.50

 HOURS

2.29

 horas

2.26

Activations Density 0.153%

references to time durations

No Comments

No Known Activations