INDEX

Explanations

references to winning prestigious competitions or awards

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

ITNESS

-0.65

 dele

-0.59

inventoryQuantity

-0.59

Lear

-0.57

 memos

-0.57

 silhou

-0.56

 PowerPoint

-0.56

 timelines

-0.56

 obser

-0.56

 horizon

-0.56

POSITIVE LOGITS

 convinc

1.07

 outright

1.06

 decisively

0.99

 twice

0.94

 unanimously

0.93

 effortlessly

0.86

 despite

0.86

 consecut

0.86

 ç¥ŀ

0.84

 thanks

0.83

Activations Density 0.196%

references to winning prestigious competitions or awards

No Comments

No Known Activations