INDEX

Explanations

phrases related to poor quality or performance

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

ategory

-0.84

ubi

-0.81

SPONSORED

-0.80

Pi

-0.77

Ru

-0.68

irs

-0.67

":[

-0.66

{:

-0.66

pta

-0.66

CU

-0.66

POSITIVE LOGITS

 quality

1.15

 hygiene

1.11

 judgement

0.98

 luck

0.96

 manners

0.95

 imitation

0.94

 digestion

0.91

 performers

0.91

 judgment

0.90

quality

0.90

Activations Density 0.064%

phrases related to poor quality or performance

No Comments

No Known Activations