INDEX

Explanations

prepositions and articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 same

-0.67

 Yoshida

-0.63

 latter

-0.62

 pula

-0.61

 intere

-0.59

ौर

-0.59

 Claude

-0.58

 model

-0.57

 more

-0.57

 work

-0.56

POSITIVE LOGITS

the

1.17

GraphicsUnit

1.03

+#+

0.98

__(/*!

0.96

+#+#

0.96

 consultato

0.90

PositiveButton

0.89

Portail

0.86

 את

0.85

 ristoranti

0.85

Activations Density 0.528%

prepositions and articles

No Comments

No Known Activations