INDEX

Explanations

phrases related to uncertainty or possibility

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

 mathemat

-0.68

ģĸ

-0.68

ngth

-0.65

 gratification

-0.64

icka

-0.59

 resusc

-0.59

 merry

-0.58

cffffcc

-0.58

 buildup

-0.58

 hoop

-0.57

POSITIVE LOGITS

not

1.16

not

1.15

Not

1.06

Not

0.92

NOT

0.90

é¾įå

0.76

acular

0.71

act

0.69

å¦

0.68

actor

0.67

Activations Density 0.257%

phrases related to uncertainty or possibility

No Comments

No Known Activations