INDEX

Explanations

phrases indicating uncertainty or lack of clarity in a statement

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

fulness

-0.65

rence

-0.65

HAHAHAHA

-0.59

"""

-0.58

cellence

-0.57

olon

-0.56

die

-0.56

lite

-0.56

 commits

-0.55

multi

-0.55

POSITIVE LOGITS

 unclear

1.70

 unknown

1.16

 speculated

1.15

 conceivable

1.12

 believed

1.09

 uncertain

1.07

 doubtful

1.00

 possible

0.95

 estimated

0.94

 unlikely

0.93

Activations Density 0.134%

phrases indicating uncertainty or lack of clarity in a statement

No Comments

No Known Activations