INDEX

Explanations

hash symbols used in code documentation or comments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

-0.75

-0.71

-0.67

—

-0.66

•

-0.65

-0.64

-0.63

POSITIVE LOGITS

 pleaſure

1.26

 itſelf

1.25

 Monfieur

1.24

 ainfi

1.20

 ſtate

1.17

 myſelf

1.16

 photolibrary

1.15

 étoient

1.15

 Jefus

1.14

 Majefty

1.12

Activations Density 1.471%

hash symbols used in code documentation or comments

No Comments

No Known Activations