INDEX

Explanations

negations or contradictions in statements

oai_token-act-pair · gpt-3.5-turbo

negations or phrases indicating something is not true or not allowed

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

å¥

-0.80

éĹĺ

-0.76

 Tours

-0.67

 Laws

-0.66

éĥ

-0.65

kamp

-0.64

èĪ

-0.64

ership

-0.64

 Might

-0.64

çļ

-0.63

POSITIVE LOGITS

 necessarily

1.34

icably

1.24

icable

1.21

epad

1.03

 exactly

1.02

eworthy

1.01

withstanding

1.01

orious

0.96

yet

0.96

 bothered

0.93

Activations Density 0.155%

negations or contradictions in statements

negations or phrases indicating something is not true or not allowed

No Comments

No Known Activations