INDEX

Explanations

phrases related to the concept of "what."

oai_token-act-pair · gpt-3.5-turbo

questions or statements regarding definitions or clarifications of concepts

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

Not in Any Lists

No Comments

Negative Logits

enburg

-0.81

gur

-0.65

jee

-0.65

robe

-0.64

gi

-0.63

xon

-0.63

enberg

-0.62

ster

-0.62

ulic

-0.61

Jet

-0.61

POSITIVE LOGITS

 happened

1.23

 happens

1.21

 transpired

1.18

soever

1.18

 constitutes

1.06

 kinds

0.95

 else

0.94

 constituted

0.92

 separates

0.91

 happ

0.90

Activations Density 0.092%

phrases related to the concept of "what."

questions or statements regarding definitions or clarifications of concepts

No Comments

No Known Activations