INDEX

Explanations

the word "nothing" paired with a comparative or superlative word

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a lack of value or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

eus

-0.70

cens

-0.60

leading

-0.57

ATIONS

-0.57

CDC

-0.56

ivation

-0.56

 Roots

-0.55

 anonymity

-0.53

leaders

-0.53

oise

-0.53

POSITIVE LOGITS

 compared

0.89

ĸļ

0.77

imilar

0.76

 remotely

0.74

®

0.68

galitarian

0.67

¹

0.67

 else

0.66

ĪĴ

0.66

¬

0.66

Activations Density 0.049%

the word "nothing" paired with a comparative or superlative word

phrases indicating a lack of value or significance

No Comments

No Known Activations