INDEX

Explanations

phrases related to cooperation and unity

oai_token-act-pair · gpt-3.5-turbo

conjunctions, particularly the word "and," indicating connections or additions in the text

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

ļéĨĴ

-0.77

idge

-0.74

wright

-0.74

Wire

-0.74

zan

-0.73

Newsletter

-0.70

 Seen

-0.70

 Pigs

-0.68

Cola

-0.67

Tickets

-0.66

POSITIVE LOGITS

 majesty

1.09

 complexities

1.06

 richness

1.04

 effectiveness

1.03

 intric

1.02

 usefulness

0.99

 complexity

0.99

 plight

0.99

 antics

0.98

 brilliance

0.98

Activations Density 0.123%

phrases related to cooperation and unity

conjunctions, particularly the word "and," indicating connections or additions in the text

No Comments

No Known Activations