INDEX

Explanations

keywords related to specific locations and entities, such as "New York", "Apple", "Japan", "Lebanese", etc

oai_token-act-pair · gpt-3.5-turbo

specific place names and proper nouns

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 constitu

-0.69

é¾

-0.68

é¾įåĸļå£«

-0.67

æĸ¹

-0.63

éļ

-0.62

ç«

-0.60

senal

-0.59

ettel

-0.59

å¦

-0.59

anse

-0.58

POSITIVE LOGITS

ico

0.59

 Morty

0.59

or

0.58

0.56

and

0.51

onda

0.51

 Pizza

0.50

 Brad

0.49

Â®,

0.48

Activations Density 1.408%

keywords related to specific locations and entities, such as "New York", "Apple", "Japan", "Lebanese", etc

specific place names and proper nouns

No Comments

No Known Activations