INDEX

Explanations

specific phrases related to legality and actions regarding breaking the law

oai_token-act-pair · gpt-3.5-turbo

keywords associated with health, outcomes, and progress

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Trin

-0.60

 Quebec

-0.57

 Jude

-0.54

 Torment

-0.52

 Entered

-0.52

 Hull

-0.51

 Quartz

-0.51

 Toledo

-0.49

 Uncharted

-0.49

Cu

-0.49

POSITIVE LOGITS

è¦ļéĨĴ

0.78

FORE

0.74

ilib

0.70

ignty

0.69

ardless

0.68

etheless

0.68

©¶æ

0.67

isode

0.66

vertisement

0.66

escription

0.66

Activations Density 1.620%

specific phrases related to legality and actions regarding breaking the law

keywords associated with health, outcomes, and progress

No Comments

No Known Activations