INDEX

Explanations

adjectives indicating extremeness or intensity

oai_token-act-pair · gpt-3.5-turbo

intensifiers that emphasize the degree of something being described

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

osal

-0.69

enegger

-0.68

Bei

-0.66

è¦ļéĨĴ

-0.63

ourses

-0.62

 Tanz

-0.61

ioch

-0.60

 Xeon

-0.59

OC

-0.59

OW

-0.59

POSITIVE LOGITS

technical

0.81

very

0.81

STEM

0.81

icult

0.79

interesting

0.76

 informative

0.75

much

0.75

geoning

0.71

 technical

0.69

-----------

0.69

Activations Density 0.015%

adjectives indicating extremeness or intensity

intensifiers that emphasize the degree of something being described

No Comments

No Known Activations