INDEX

Explanations

declines, trends, and extinction of various phenomena in different contexts

oai_token-act-pair · gpt-3.5-turbo

indicators of decline or downward trends 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 oath

-0.75

 entert

-0.70

 goggles

-0.64

 optionally

-0.64

 exerc

-0.63

 aloud

-0.63

 instructions

-0.63

 waive

-0.62

 waived

-0.60

vo

-0.60

POSITIVE LOGITS

 decline

1.13

 trends

1.03

 declines

1.00

 trend

0.99

 declining

0.95

 uptake

0.94

rowth

0.90

 growth

0.90

Population

0.90

 prevalence

0.89

Activations Density 1.009%

declines, trends, and extinction of various phenomena in different contexts

indicators of decline or downward trends in various contexts

No Comments

No Known Activations