INDEX

Explanations

terms associated with specific attributes, characteristics, or conditions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating association or connection

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

Reviewed

-0.73

matched

-0.69

anke

-0.69

ynes

-0.68

xtap

-0.68

olit

-0.67

NB

-0.64

iger

-0.64

JJ

-0.61

ights

-0.61

POSITIVE LOGITS

 regards

0.73

 Bohem

0.68

è¦ļéĨĴ

0.65

 Deity

0.65

ryan

0.65

 extinction

0.63

ricular

0.63

anas

0.62

illac

0.62

 Scion

0.62

Activations Density 0.080%

terms associated with specific attributes, characteristics, or conditions

phrases indicating association or connection

No Comments

No Known Activations