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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 projecting

-0.79

Osc

-0.72

 indo

-0.66

å¥³

-0.64

 unprotected

-0.64

inese

-0.63

 projected

-0.63

 diver

-0.62

IDER

-0.61

 deviation

-0.61

POSITIVE LOGITS

gements

1.10

gments

1.05

giving

0.96

ifully

0.86

gment

0.85

ments

0.85

 acknowled

0.84

 heavens

0.83

fulness

0.81

ees

0.80

Activations Density 0.015%

expressions of gratitude or thanks

expressions of gratitude

No Comments

No Known Activations