INDEX

Explanations

phrases indicating the concept of greater good and moral principles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

COUVER

-0.89

QMetaType

-0.69

出版年

-0.63

WriteAttribute

-0.60

########.

-0.57

uxxxx

-0.56

+#+#

-0.54

 transférez

-0.54

TagMode

-0.53

webElementGuid

-0.52

POSITIVE LOGITS

 good

3.88

good

3.62

Good

3.45

 Good

3.33

GOOD

3.13

 GOOD

3.12

 buena

2.21

 buenas

2.07

 bonne

2.06

 gute

2.02

Activations Density 0.890%

phrases indicating the concept of greater good and moral principles

No Comments

No Known Activations