INDEX

Explanations

the word "not" being emphasized in sentences

oai_token-act-pair · gpt-3.5-turbo

negations or expressions of denial

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

stakes

-0.69

éĥ

-0.68

 Companies

-0.67

 Presence

-0.65

ership

-0.65

itor

-0.65

 Tours

-0.64

iers

-0.61

ãĤ¼

-0.61

 Circuit

-0.61

POSITIVE LOGITS

icably

1.37

 necessarily

1.28

icable

1.17

epad

1.14

hin

1.03

orious

0.95

 exactly

0.93

yet

0.89

 uncommon

0.88

eworthy

0.88

Activations Density 0.179%

the word "not" being emphasized in sentences

negations or expressions of denial

No Comments

No Known Activations