INDEX

Explanations

phrases related to war and suffering

oai_token-act-pair · gpt-3.5-turbo

instances of hyphenated phrases or terms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

opher

-0.69

oshop

-0.67

 preference

-0.67

åŃĲ

-0.65

ously

-0.62

 arena

-0.61

 constitu

-0.61

umbers

-0.61

 newcomer

-0.61

zbek

-0.60

POSITIVE LOGITS

_-

1.67

webkit

1.02

=-=-=-=-

0.86

âĢ¢âĢ¢

0.85

=-=-=-=-=-=-=-=-

0.83

taboola

0.78

/-

0.78

something

0.75

including

0.74

âĸº

0.74

Activations Density 0.069%

phrases related to war and suffering

instances of hyphenated phrases or terms

No Comments

No Known Activations