INDEX

Explanations

phrases related to time frames, specifically emphasizing "few"

oai_token-act-pair · gpt-3.5-turbo

the phrase "a few" to indicate small quantities or timeframes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

acus

-0.82

 agre

-0.78

yrinth

-0.73

 destro

-0.69

 conclud

-0.68

leneck

-0.66

alam

-0.66

ican

-0.64

webkit

-0.64

ilon

-0.61

POSITIVE LOGITS

 dozen

1.41

 hundred

1.36

 thousand

1.20

 weeks

1.10

teenth

1.02

dozen

1.02

 days

0.98

 minutes

0.98

 months

0.98

 nights

0.95

Activations Density 0.047%

phrases related to time frames, specifically emphasizing "few"

the phrase "a few" to indicate small quantities or timeframes

No Comments

No Known Activations