INDEX

Explanations

words related to consequences and their implications

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Negative Logits

 للمعارف

-0.79

 Jock

-0.79

 Wiktionnaire

-0.78

 protoimpl

-0.71

 InputDecoration

-0.71

SwingConstants

-0.71

 INTERESAR

-0.70

 Harlow

-0.69

irkus

-0.68

swire

-0.67

POSITIVE LOGITS

 consequences

1.13

 CONSEQU

1.12

 Consequences

1.11

Consequences

1.11

 consequence

0.91

————————————————

0.84

 conséquences

0.84

sequences

0.78

 consecuencias

0.77

“

0.75

Activations Density 0.008%

words related to consequences and their implications

No Known Activations