INDEX

Explanations

phrases related to examination and analysis processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 astore

-0.54

fontaine

-0.54

ImageField

-0.51

 Eternal

-0.51

 كنت

-0.50

cipar

-0.50

Mil

-0.50

astify

-0.49

olina

-0.49

mil

-0.49

POSITIVE LOGITS

 examine

1.16

 examining

1.12

 Examine

1.10

 examines

1.08

Examine

1.07

 examined

1.04

examined

1.04

 Examining

1.01

examine

1.00

 examin

1.00

Activations Density 0.556%

phrases related to examination and analysis processes

No Comments

No Known Activations