INDEX

Explanations

negations or phrases indicating the absence of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Steck

-0.64

 Laird

-0.62

-0.59

 cime

-0.59

 Chau

-0.57

miu

-0.57

 Jinping

-0.56

 Luiz

-0.56

ervo

-0.56

POSITIVE LOGITS

NOT

1.37

NOT

1.23

Not

1.22

Not

1.20

not

1.15

isNot

0.92

ENOT

0.83

assertNot

0.81

IsNot

0.79

not

0.78

Activations Density 0.122%

negations or phrases indicating the absence of something

No Comments

No Known Activations