INDEX

Explanations

phrases indicating completion or conclusion

oai_token-act-pair · gpt-3.5-turbo

instances of the word "over" indicating completion or end of situations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 partName

-0.73

AMA

-0.71

 Forward

-0.65

Express

-0.61

 forwards

-0.61

yssey

-0.60

 interacts

-0.60

osity

-0.60

ãĥı

-0.59

 Likes

-0.59

POSITIVE LOGITS

rated

1.11

priced

1.03

blown

1.03

stated

1.00

kill

1.00

reaching

0.98

haul

0.96

whelming

0.95

loading

0.95

whel

0.94

Activations Density 0.039%

phrases indicating completion or conclusion

instances of the word "over" indicating completion or end of situations

No Comments

No Known Activations