INDEX

Explanations

questions or statements expressing curiosity or seeking information

oai_token-act-pair · gpt-3.5-turbo

inquiries or questions about knowledge and understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ItemTracker

-0.84

ĪĴ

-0.80

phrine

-0.75

ovie

-0.74

ascus

-0.73

onite

-0.68

interstitial

-0.67

onding

-0.67

ŃĶ

-0.67

ouri

-0.65

POSITIVE LOGITS

ledge

1.11

how

0.99

 ABOUT

0.92

why

0.89

WHY

0.87

 beforehand

0.85

 about

0.84

HOW

0.82

iquette

0.81

 whether

0.79

Activations Density 0.059%

questions or statements expressing curiosity or seeking information

inquiries or questions about knowledge and understanding

No Comments

No Known Activations