INDEX

Explanations

phrases related to official reports or statements

oai_token-act-pair · gpt-3.5-turbo

the article "a" in various contexts related to reports and statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

-0.86

ãĤ¼ãĤ¦ãĤ¹

-0.73

 Jagu

-0.73

âĢİ

-0.67

agree

-0.66

enaries

-0.66

anamo

-0.66

oids

-0.65

icably

-0.65

cal

-0.65

POSITIVE LOGITS

 statement

0.99

 spokeswoman

0.98

 recent

0.96

 spokesman

0.95

 slew

0.95

 report

0.93

 knowledgeable

0.93

 spokesperson

0.92

 biography

0.91

 dozen

0.88

Activations Density 0.191%

phrases related to official reports or statements

the article "a" in various contexts related to reports and statements

No Comments

No Known Activations