INDEX

Explanations

phrases discussing principles and concepts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hoebe

-0.64

aget

-0.63

lotte

-0.62

дарь

-0.61

AWAY

-0.61

 Ediciones

-0.61

bamos

-0.60

tilde

-0.60

Weh

-0.59

away

-0.58

POSITIVE LOGITS

 principles

2.18

 Principles

2.07

 principle

2.06

Principles

2.00

principles

1.98

 Principle

1.96

 PRINCIPLES

1.88

principle

1.83

Principle

1.81

 PRINCIP

1.67

Activations Density 0.058%

phrases discussing principles and concepts

No Comments

No Known Activations