INDEX

Explanations

mentions of specific businesses, particularly Trader Joe's and McDonald's

oai_token-act-pair · gpt-3.5-turbo

the possessive form of the word "Joe."

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

aneously

-0.79

llor

-0.77

wordpress

-0.68

Downloadha

-0.66

hari

-0.66

rait

-0.65

 occasion

-0.63

ãĥĥãĥī

-0.63

ENN

-0.63

anguage

-0.62

POSITIVE LOGITS

 Mansion

0.84

own

0.77

 busiest

0.76

 Crossing

0.75

eyes

0.75

 newest

0.75

 Creek

0.74

 Bees

0.73

 Syndrome

0.73

 finest

0.73

Activations Density 0.094%

mentions of specific businesses, particularly Trader Joe's and McDonald's

the possessive form of the word "Joe."

No Comments

No Known Activations