INDEX

Explanations

phrases that are intended to draw the reader's attention to additional or related information

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "also."

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

slot

-0.72

acious

-0.68

acity

-0.66

agus

-0.65

eers

-0.64

itiveness

-0.64

ylum

-0.64

anse

-0.63

aciously

-0.62

atics

-0.62

POSITIVE LOGITS

 noteworthy

0.95

 notable

0.84

 included

0.74

 Known

0.73

 includ

0.73

 includes

0.69

 Called

0.68

 notor

0.67

 interestingly

0.66

 Included

0.66

Activations Density 0.038%

phrases that are intended to draw the reader's attention to additional or related information

the repeated use of the word "also."

No Known Activations