INDEX

Explanations

dates in a particular format

oai_token-act-pair · gpt-3.5-turbo

numerical values associated with significant events or characteristics

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

 dissu

-0.66

itters

-0.64

utical

-0.63

 sacrificing

-0.60

 deceived

-0.59

esty

-0.59

 doct

-0.58

 whine

-0.58

 underestimate

-0.58

 temptation

-0.58

POSITIVE LOGITS

Contents

1.05

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

1.03

ÂłÂłÂłÂł

1.03

ÂłÂłÂł

1.02

ÂłÂłÂłÂłÂłÂłÂłÂł

0.94

Born

0.88

ccording

0.88

Trivia

0.85

History

0.79

SPONSORED

0.79

Activations Density 0.463%

dates in a particular format

numerical values associated with significant events or characteristics

No Comments

No Known Activations