INDEX

Explanations

phrases related to efforts to prevent negative outcomes

oai_token-act-pair · gpt-3.5-turbo

variations of the word "stymie" and related concepts of hindrance or obstruction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

catentry

-0.78

 DRAG

-0.68

 herald

-0.65

ITNESS

-0.65

 Administ

-0.64

FontSize

-0.63

ternity

-0.63

 timelines

-0.62

 timeline

-0.61

irlf

-0.60

POSITIVE LOGITS

helm

0.88

warts

0.86

ggle

0.85

wart

0.81

iasis

0.80

bery

0.79

gered

0.79

ulence

0.79

ulent

0.79

 Gupta

0.77

Activations Density 0.038%

phrases related to efforts to prevent negative outcomes

variations of the word "stymie" and related concepts of hindrance or obstruction

No Comments

No Known Activations