INDEX

Explanations

phrases indicating an extended period of time

oai_token-act-pair · gpt-3.5-turbo

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

Contents

-0.74

Agg

-0.68

grounds

-0.66

align

-0.65

orders

-0.64

Instruct

-0.64

peed

-0.63

Own

-0.63

Att

-0.62

rules

-0.61

POSITIVE LOGITS

 reason

0.97

 variety

0.95

 multitude

0.94

 sake

0.92

 couple

0.90

 duration

0.90

 period

0.90

decade

0.89

 foreseeable

0.87

few

0.87

Activations Density 0.131%

phrases indicating an extended period of time

No Comments

No Known Activations