INDEX

Explanations

news headlines or article titles

oai_token-act-pair · gpt-3.5-turbo

the word "More" and its variations, indicating a focus on additional content or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

keeping

-0.74

atan

-0.71

-0.68

same

-0.68

ãĥ¼ãĥĨ

-0.68

Enlarge

-0.66

ļé

-0.65

xtap

-0.64

liest

-0.64

idated

-0.63

POSITIVE LOGITS

 importantly

1.24

ado

1.12

 Than

1.00

 than

0.98

 interesting

0.80

 sophisticated

0.79

 important

0.78

 stringent

0.77

 mature

0.75

 elaborate

0.74

Activations Density 0.062%

news headlines or article titles

the word "More" and its variations, indicating a focus on additional content or information

No Comments

No Known Activations