INDEX

Explanations

words related to temporal sequences or events that occur prior to others

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

Not in Any Lists

No Comments

Negative Logits

 habet

-0.83

__":

-0.80

ſelf

-0.79

KommentareTeilen

-0.73

gany

-0.71

 Jefus

-0.71

ษัท

-0.69

%)$

-0.68

gdx

-0.68

 følge

-0.65

POSITIVE LOGITS

 before

1.96

before

1.82

 Before

1.71

 BEFORE

1.70

BEFORE

1.67

Before

1.63

 sebelum

1.59

 befo

1.37

 antes

1.35

 πριν

1.35

Activations Density 0.694%

words related to temporal sequences or events that occur prior to others

No Comments

No Known Activations