INDEX

Explanations

specific dates mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Walters

-0.65

Poc

-0.63

 clientèle

-0.61

-0.60

Taz

-0.60

 bouch

-0.59

utentic

-0.58

ربعة

-0.57

Peng

-0.57

 Whitaker

-0.57

POSITIVE LOGITS

 June

2.01

June

2.00

JUNE

1.90

 JUNE

1.83

 june

1.58

june

1.48

 juin

1.46

 giugno

1.42

July

1.41

 July

1.40

Activations Density 0.046%

specific dates mentioned in the text

No Comments

No Known Activations