INDEX

Explanations

questions and expressions of surprise

oai_token-act-pair · gpt-3.5-turbo

expressions of surprise or disbelief

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

•layer 8 - surprise

No Comments

Negative Logits

 diffusion

-0.72

ezvous

-0.71

 preference

-0.64

 coasts

-0.59

idem

-0.58

 favors

-0.58

 Nieto

-0.58

 mutually

-0.58

aturday

-0.56

 liber

-0.55

POSITIVE LOGITS

?!

1.09

?!"

1.05

?)

1.00

Huh

1.00

???

0.99

?".

0.97

!?"

0.96

Why

0.96

?).

0.95

!?

0.94

Activations Density 0.446%

questions and expressions of surprise

expressions of surprise or disbelief

No Comments

No Known Activations