INDEX

Explanations

phrases or sentences warning about the content of the text

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the presence of content or materials within various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

doms

-0.79

 Sabha

-0.75

apo

-0.69

urai

-0.67

 Seym

-0.65

icably

-0.65

laus

-0.64

sett

-0.63

liner

-0.63

zai

-0.62

POSITIVE LOGITS

ttes

0.77

 contents

0.76

ãĤ¼ãĤ¦ãĤ¹

0.73

encies

0.72

 Contains

0.72

ãĤ©

0.69

ãĤ£

0.69

iveness

0.68

Material

0.68

ãĤ·ãĥ£

0.67

Activations Density 0.024%

phrases or sentences warning about the content of the text

phrases indicating the presence of content or materials within various contexts

No Comments

No Known Activations