INDEX

Explanations

negative descriptors related to quality or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

énario

-0.77

 Bourgoin

-0.73

 demeure

-0.69

 chá

-0.64

رشف

-0.63

omock

-0.62

 wireType

-0.62

Reis

-0.62

 recorrer

-0.61

 ویکی‌پدیا

-0.61

POSITIVE LOGITS

bad

3.84

Bad

3.41

Bad

3.37

bad

3.33

BAD

3.10

BAD

2.75

 mauvaise

1.94

 mauvais

1.83

 schlechte

1.77

 badly

1.76

Activations Density 0.049%

negative descriptors related to quality or conditions

No Comments

No Known Activations