INDEX

Explanations

phrases indicating a completion or conclusion

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize the concept of "it" or refer to specific actions or occurrences

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

particularly

-0.67

rador

-0.64

utive

-0.60

ĸļ

-0.58

otos

-0.58

lean

-0.57

ãĥĻ

-0.56

arlane

-0.55

cia

-0.55

burning

-0.55

POSITIVE LOGITS

1.11

 folks

1.03

!:

1.02

!!!!

0.98

!!

0.95

!!!

0.94

!!!!!

0.92

!!!!!!!!

0.91

 again

0.89

!.

0.88

Activations Density 0.302%

phrases indicating a completion or conclusion

phrases that emphasize the concept of "it" or refer to specific actions or occurrences

No Comments

No Known Activations