INDEX

Explanations

phrases where something is being done to something else, particularly with a critical perspective

oai_token-act-pair · gpt-3.5-turbo

the conjunction "and" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

.'"

-0.54

abul

-0.50

igmatic

-0.50

DonaldTrump

-0.50

wright

-0.49

bub

-0.49

actionDate

-0.49

fur

-0.49

!'"

-0.47

'."

-0.47

POSITIVE LOGITS

 thus

0.73

 thereby

0.73

 consequently

0.72

 hence

0.71

 secondly

0.70

 therefore

0.68

 THEN

0.63

 possibly

0.62

 then

0.62

 thence

0.60

Activations Density 0.428%

phrases where something is being done to something else, particularly with a critical perspective

the conjunction "and" in various contexts

No Comments

No Known Activations