INDEX

Explanations

phrases indicating suffering or negative events happening to individuals or organizations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "suffered" in relation to various contexts of distress or injuries

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

ococ

-0.68

apo

-0.64

clusive

-0.63

rouse

-0.61

clus

-0.60

aver

-0.60

uren

-0.60

itative

-0.59

 Leilan

-0.58

send

-0.58

POSITIVE LOGITS

 setbacks

1.01

 losses

0.82

BAT

0.81

 injuries

0.81

 bouts

0.80

nces

0.76

 horrend

0.75

 burns

0.73

 headaches

0.72

acus

0.72

Activations Density 0.024%

phrases indicating suffering or negative events happening to individuals or organizations

instances of the word "suffered" in relation to various contexts of distress or injuries

No Comments

No Known Activations