INDEX

Explanations

phrases indicating a comparative relationship, specifically emphasizing a lesser degree of something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "much" and related concepts of degree or extent

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

},{"

-0.65

)|

-0.60

orage

-0.60

ipeg

-0.59

âĿ

-0.57

Kun

-0.57

isan

-0.56

ilege

-0.56

ADVERTISEMENT

-0.56

atile

-0.56

POSITIVE LOGITS

 preferring

1.07

etheless

0.92

 culminating

0.92

 suggesting

0.92

 notwithstanding

0.90

pecially

0.89

 evidenced

0.87

 noting

0.86

 permitting

0.86

 implying

0.85

Activations Density 0.387%

phrases indicating a comparative relationship, specifically emphasizing a lesser degree of something

instances of the word "much" and related concepts of degree or extent

No Known Activations