INDEX

Explanations

numeric values within texts, such as years, percentages, or quantities

oai_token-act-pair · gpt-3.5-turbo

instances of the letter "A" at the beginning of sentences or phrases

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Contents

-0.73

antry

-0.72

Finish

-0.69

Area

-0.68

agents

-0.67

pees

-0.66

acid

-0.65

anism

-0.63

 Presents

-0.63

 dishes

-0.62

POSITIVE LOGITS

cknowled

1.13

 recent

1.12

 curs

1.06

 handful

1.01

usterity

1.01

decade

0.99

 study

0.99

 survey

0.99

 glance

0.98

 whopping

0.97

Activations Density 0.190%

numeric values within texts, such as years, percentages, or quantities

instances of the letter "A" at the beginning of sentences or phrases

No Comments

No Known Activations