INDEX

Explanations

phrases related to added value or additional features

oai_token-act-pair · gpt-3.5-turbo

the indefinite article "a" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Events

-0.79

flies

-0.76

scenes

-0.75

notes

-0.75

AIDS

-0.74

votes

-0.73

evidence

-0.73

 alliances

-0.73

Contents

-0.72

facts

-0.72

POSITIVE LOGITS

 typical

1.10

 traditional

1.01

 normal

0.98

 single

0.95

 regular

0.94

 conventional

0.92

 standalone

0.91

 beginner

0.87

 reputable

0.85

lot

0.84

Activations Density 0.352%

phrases related to added value or additional features

the indefinite article "a" in various contexts

No Comments

No Known Activations