INDEX

Explanations

the word "am" followed by a verb

oai_token-act-pair · gpt-3.5-turbo

the word "am" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 aver

-0.72

 takeaway

-0.69

DragonMagazine

-0.69

ttes

-0.68

 Alley

-0.67

 learners

-0.66

EStreamFrame

-0.61

 Regions

-0.61

 stakes

-0.60

 concession

-0.60

POSITIVE LOGITS

sterdam

1.26

ethyst

1.21

azon

1.19

ajor

1.14

endment

1.11

essage

1.03

assing

1.01

ateurs

1.00

nesty

0.97

ilies

0.97

Activations Density 0.031%

the word "am" followed by a verb

the word "am" in various contexts

No Comments

No Known Activations