INDEX

Explanations

strong emotional reactions such as being saddened, disappointed, appalled, horrified, or shocked

oai_token-act-pair · gpt-3.5-turbo

expressions of strong negative emotions, particularly sadness, disappointment, and horror

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 livest

-0.69

 cheat

-0.68

Ranked

-0.67

enture

-0.67

soDeliveryDate

-0.66

pmwiki

-0.66

 dated

-0.65

checks

-0.63

 sneak

-0.63

sites

-0.62

POSITIVE LOGITS

 aback

0.85

vier

0.74

 saddened

0.73

dy

0.72

urous

0.69

 citiz

0.66

 enough

0.66

ORK

0.65

 seeing

0.64

ãĤ¦ãĤ¹

0.64

Activations Density 0.086%

strong emotional reactions such as being saddened, disappointed, appalled, horrified, or shocked

expressions of strong negative emotions, particularly sadness, disappointment, and horror

No Comments

No Known Activations