INDEX

Explanations

question marks signaling uncertainty or inquiries

oai_token-act-pair · gpt-3.5-turbo

questions with a focus on penalties or rules

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

 encount

-0.80

 marsh

-0.76

apan

-0.70

ank

-0.69

alist

-0.68

neau

-0.68

ENTS

-0.67

 arrang

-0.64

 harness

-0.64

 corrid

-0.64

POSITIVE LOGITS

 Nope

1.24

Nah

1.01

Huh

0.98

.?

0.97

 Probably

0.97

 Absolutely

0.93

Yep

0.93

Yes

0.89

 Possibly

0.89

 Didn

0.89

Activations Density 0.102%

question marks signaling uncertainty or inquiries

questions with a focus on penalties or rules

No Comments

No Known Activations