INDEX

Explanations

interrogative sentences ending in 'it' with an emphasis on high activation values

oai_token-act-pair · gpt-3.5-turbo

rhetorical questions and conversational phrases

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

furt

-0.79

umbn

-0.66

eric

-0.64

izont

-0.63

aeper

-0.60

orsi

-0.60

Stand

-0.60

ternity

-0.59

esm

-0.57

aneers

-0.57

POSITIVE LOGITS

?!

0.95

0.88

!?

0.82

??

0.81

?!"

0.79

0.76

?'

0.74

 adorable

0.73

!?"

0.73

?"

0.72

Activations Density 0.042%

interrogative sentences ending in 'it' with an emphasis on high activation values

rhetorical questions and conversational phrases

No Comments

No Known Activations