INDEX

Explanations

expressions of gratitude or thanks

oai_token-act-pair · gpt-3.5-turbo

expressions of gratitude

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Inferno

-0.73

 Construct

-0.71

cpp

-0.66

wide

-0.64

 Samoa

-0.64

 Ultron

-0.64

 Fires

-0.64

etc

-0.63

 Scorpion

-0.61

Ai

-0.60

POSITIVE LOGITS

 thank

1.12

ĸļ

0.97

 thanking

0.93

 acknowled

0.90

gements

0.89

giving

0.86

 thanked

0.86

gments

0.85

ifully

0.85

 THANK

0.80

Activations Density 0.013%

expressions of gratitude or thanks

expressions of gratitude

No Comments

No Known Activations