INDEX

Explanations

expressions of gratitude

oai_token-act-pair · gpt-3.5-turbo

expressions of gratitude and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

agate

-0.73

oto

-0.67

improve

-0.65

FO

-0.62

etc

-0.62

calling

-0.62

change

-0.61

analy

-0.60

uter

-0.59

smoking

-0.59

POSITIVE LOGITS

giving

0.97

 acknowled

0.96

gements

0.87

 citiz

0.86

 pardon

0.83

FUL

0.79

 acknowledgment

0.78

fulness

0.77

 gratitude

0.77

ledged

0.77

Activations Density 0.017%

expressions of gratitude

expressions of gratitude and appreciation

No Comments

No Known Activations