INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "is"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 stakes

-0.67

 thumbnail

-0.64

¥ŀ

-0.63

ruciating

-0.59

 downt

-0.58

 oats

-0.57

¥µ

-0.55

 nick

-0.54

MFT

-0.54

 allotted

-0.54

POSITIVE LOGITS

abeth

1.31

earch

1.06

ection

1.05

ystem

1.02

ource

1.02

aurus

1.01

peed

0.99

terness

0.99

kell

0.98

TRY

0.96

Activations Density 0.062%

proper nouns

occurrences of the word "is"

No Comments

No Known Activations