INDEX

Explanations

verbs in present tense that are negated or preceded by "not"

oai_token-act-pair · gpt-3.5-turbo

phrases that include the word "does" along with negations and expressions of limitation

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 palms

-0.71

isu

-0.69

 Learns

-0.68

boarding

-0.67

 Styles

-0.62

 COUR

-0.61

 Ready

-0.61

 Plans

-0.60

 Canal

-0.60

)=(

-0.60

POSITIVE LOGITS

vet

1.05

oms

1.00

NOT

0.97

not

0.96

 exist

0.95

actic

0.94

omsday

0.93

oming

0.89

ppel

0.88

 indeed

0.87

Activations Density 0.105%

verbs in present tense that are negated or preceded by "not"

phrases that include the word "does" along with negations and expressions of limitation

No Known Activations