INDEX

Explanations

various forms of the word "learn" and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Ỉ

-0.76

BoxShadow

-0.69

zhe

-0.69

ActionEvent

-0.67

 Nilsson

-0.65

pflich

-0.63

queline

-0.63

setAccessible

-0.63

 चीज़ों

-0.62

DotNetBar

-0.61

POSITIVE LOGITS

 LEARN

1.43

LEARN

1.41

 learns

1.37

Lear

1.37

learn

1.34

Learn

1.32

 learning

1.31

 Learning

1.31

 Lear

1.30

 learn

1.29

Activations Density 0.052%

various forms of the word "learn" and related concepts

No Comments

No Known Activations