INDEX

Explanations

dates or time-related phrases

oai_token-act-pair · gpt-3.5-turbo

references to historical or factual data related to organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ħĭ

-0.84

endif

-0.83

 sqor

-0.72

else

-0.67

padding

-0.66

margin

-0.66

"],"

-0.63

alon

-0.63

too

-0.62

 endif

-0.61

POSITIVE LOGITS

 inception

1.37

 originated

1.32

 origins

1.22

 origin

1.19

 started

1.18

 originate

1.18

 began

1.16

 arose

1.13

 beginnings

1.13

 founded

1.12

Activations Density 1.234%

dates or time-related phrases

references to historical or factual data related to organizations

No Comments

No Known Activations