INDEX

Explanations

words related to changes in quantity, quality, or degree

oai_token-act-pair · gpt-3.5-turbo

terms associated with changes in states or conditions, particularly improvements, declines, and increases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

sel

-0.74

ãĥīãĥ©

-0.72

thia

-0.71

finished

-0.71

chin

-0.70

ools

-0.69

tein

-0.68

wd

-0.67

addle

-0.66

çīĪ

-0.65

POSITIVE LOGITS

 exponentially

1.03

 markedly

0.97

 dramatically

0.95

 abruptly

0.89

 noticeably

0.89

 considerably

0.88

 drastically

0.85

 sharply

0.83

 steadily

0.80

 explos

0.78

Activations Density 0.185%

words related to changes in quantity, quality, or degree

terms associated with changes in states or conditions, particularly improvements, declines, and increases

No Comments

No Known Activations