INDEX

Explanations

specific mentions of entities or objects, such as products, images, or scenes

oai_token-act-pair · gpt-3.5-turbo

key nouns related to products, events, and notable items

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

The word or symbol after "this"

Explanation Uploaded by User

the noun in "this [noun]"

Explanation Uploaded by User

Fires on any word after the word "This" or "this"

Explanation Uploaded by User

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

\<

-0.64

--------------------------------------------------------

-0.62

_>

-0.61

actionDate

-0.61

 Doors

-0.61

DERR

-0.60

itÃ©

-0.60

CLR

-0.59

Bir

-0.58

wards

-0.57

POSITIVE LOGITS

 belongs

0.85

 represents

0.80

 lacks

0.70

 reminds

0.70

 deserves

0.69

 assumes

0.68

 demonstrates

0.68

 SHOULD

0.68

izes

0.67

OULD

0.67

Activations Density 0.271%

specific mentions of entities or objects, such as products, images, or scenes

key nouns related to products, events, and notable items

The word or symbol after "this"

the noun in "this [noun]"

Fires on any word after the word "This" or "this"

No Comments

No Known Activations