INDEX

Explanations

expressions of gratitude and acknowledgment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

bulos

-0.52

 tartalomajánló

-0.51

isat

-0.50

 Pity

-0.48

Продол

-0.46

mpu

-0.45

 Dimension

-0.45

estand

-0.43

DataAnnotations

-0.43

>",

-0.42

POSITIVE LOGITS

 thanking

0.97

 thank

0.91

 THANK

0.89

 thanked

0.87

Thank

0.80

 utafitiHapana

0.79

THANK

0.79

 remercie

0.79

windowFixed

0.78

 THANKS

0.76

Activations Density 0.099%

expressions of gratitude and acknowledgment

No Comments

No Known Activations