INDEX

Explanations

concepts and phrases related to comprehension and understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

latLng

-0.43

 liệt

-0.43

 epics

-0.41

rpc

-0.39

ambién

-0.39

 Dishes

-0.39

mobileqq

-0.39

 ephe

-0.39

 auroit

-0.39

zarchiwizowane

-0.39

POSITIVE LOGITS

 Understanding

1.23

 understanding

1.22

Understanding

1.18

 Understand

1.15

 understand

1.15

understanding

1.14

understand

1.09

 understands

1.08

Understand

1.07

 understood

0.93

Activations Density 0.123%

concepts and phrases related to comprehension and understanding

No Comments

No Known Activations