INDEX

Explanations

historical or insightful lessons gleaned from various contexts

oai_token-act-pair · gpt-3.5-turbo

references to lessons and learning experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

omin

-0.72

yy

-0.72

trak

-0.67

urat

-0.63

uve

-0.63

ãĥ¢

-0.63

gur

-0.63

 occupancy

-0.62

yip

-0.61

ãĥı

-0.60

POSITIVE LOGITS

 Learned

1.67

 learned

1.62

 learnt

1.55

 lesson

1.26

 lessons

1.22

Lear

1.12

learn

1.12

 taught

1.08

 glean

1.01

 Lessons

0.93

Activations Density 0.078%

historical or insightful lessons gleaned from various contexts

references to lessons and learning experiences

No Comments

No Known Activations