INDEX

Explanations

instances of numbers indicating a frequency or repetition of an action

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Reviewer

-0.80

affer

-0.59

abwe

-0.59

attled

-0.57

 Variable

-0.57

 agre

-0.56

ORN

-0.55

eor

-0.55

 savior

-0.54

orescence

-0.54

POSITIVE LOGITS

 times

1.69

 days

1.18

 nights

1.18

times

1.18

 years

1.18

 weeks

1.16

 months

1.16

 mornings

1.13

 miles

1.10

 kilometres

1.08

Activations Density 0.133%

instances of numbers indicating a frequency or repetition of an action

No Comments

No Known Activations