INDEX

Explanations

verbs related to receiving or absorbing information or experiences

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate inclusion or taking in something

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

ior

-0.66

eele

-0.65

ONSORED

-0.64

eller

-0.63

pas

-0.63

lat

-0.62

bia

-0.62

ga

-0.62

times

-0.61

hler

-0.61

POSITIVE LOGITS

*/(

0.83

rador

0.68

BuyableInstoreAndOnline

0.67

NetMessage

0.66

 Thumbnails

0.62

ebook

0.62

ãĥīãĥ©

0.61

 seriously

0.61

çİĭ

0.61

_-_

0.60

Activations Density 0.100%

verbs related to receiving or absorbing information or experiences

phrases that indicate inclusion or taking in something

No Comments

No Known Activations