INDEX

Explanations

phrases expressing gratitude or appreciation

oai_token-act-pair · gpt-3.5-turbo

instances where gratitude or acknowledgment is expressed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atform

-0.67

uve

-0.63

å¥³

-0.62

ength

-0.62

avis

-0.60

ille

-0.58

sci

-0.57

âĶĢâĶĢ

-0.57

]'

-0.57

abulary

-0.55

POSITIVE LOGITS

giving

1.25

 largely

0.82

to

0.71

ulously

0.71

 partly

0.70

 mainly

0.69

roxy

0.68

raltar

0.66

cription

0.66

 thankfully

0.65

Activations Density 0.024%

phrases expressing gratitude or appreciation

instances where gratitude or acknowledgment is expressed

No Comments

No Known Activations