INDEX

Explanations

phrases indicating totality or inclusivity

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a focus on comprehensiveness or entirety

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

ciation

-0.73

IDS

-0.71

FH

-0.70

knife

-0.67

yip

-0.66

reat

-0.65

aminer

-0.65

 guiIcon

-0.64

SHIP

-0.64

rouse

-0.62

POSITIVE LOGITS

ocating

1.37

uding

1.07

ocated

1.01

uring

0.96

owing

0.93

 sorts

0.93

usion

0.89

usions

0.87

 kinds

0.87

ergic

0.87

Activations Density 0.051%

phrases indicating totality or inclusivity

phrases indicating a focus on comprehensiveness or entirety

No Comments

No Known Activations