INDEX

Explanations

references to the concept of learning and educational processes

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

Ỉ

-0.73

BoxShadow

-0.71

 Rossetti

-0.68

 monoxide

-0.68

ActionEvent

-0.67

 arşivlendi

-0.66

setAccessible

-0.63

 Nilsson

-0.63

zhe

-0.62

yPos

-0.61

POSITIVE LOGITS

 learning

2.12

 Learning

2.04

learning

1.94

Learning

1.87

 LEARNING

1.80

 LEARN

1.71

 learners

1.67

LEARNING

1.67

 learn

1.65

 learns

1.63

Activations Density 0.033%

references to the concept of learning and educational processes

No Comments

No Known Activations