INDEX

Explanations

positive adjectives relating to quality

oai_token-act-pair · gpt-3.5-turbo

references to quality and performance

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

Not in Any Lists

No Comments

Negative Logits

emb

-0.71

emonium

-0.70

ha

-0.70

":[

-0.69

billion

-0.68

isSpecialOrderable

-0.67

hyde

-0.67

atum

-0.63

let

-0.62

lets

-0.62

POSITIVE LOGITS

 quality

1.19

 luck

1.02

 intentions

1.00

 deals

0.98

 grades

0.97

 rapport

0.90

 results

0.90

 outcomes

0.89

enough

0.89

 reliability

0.88

Activations Density 0.138%

positive adjectives relating to quality

references to quality and performance

No Comments

No Known Activations