INDEX

Explanations

instances of the word "more" followed by a number indicating the degree or amount of something

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the concept of "more" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

xtap

-0.72

 Classification

-0.72

-0.67

Enlarge

-0.64

pex

-0.64

Runner

-0.64

liest

-0.63

Age

-0.63

Rus

-0.62

-0.61

POSITIVE LOGITS

 than

1.36

ado

0.99

 stringent

0.96

 expensive

0.94

 sophisticated

0.89

than

0.89

 importantly

0.88

 manageable

0.88

 complicated

0.87

 efficient

0.87

Activations Density 0.163%

instances of the word "more" followed by a number indicating the degree or amount of something

phrases emphasizing the concept of "more" in various contexts

No Comments

No Known Activations