INDEX

Explanations

sentences conveying emotional intensity or urgency

oai_token-act-pair · gpt-3.5-turbo

punctuated statements and exclamations in the text

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

Period at the end of short sentences.

Explanation Uploaded by User

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 disadvantage

-0.85

 conclud

-0.83

 advantage

-0.78

 proport

-0.77

pse

-0.76

 skelet

-0.75

 advoc

-0.74

 compr

-0.73

 encount

-0.72

ascus

-0.72

POSITIVE LOGITS

 Literally

1.43

 Lots

1.28

 Seriously

1.22

 Everywhere

1.18

 Yeah

1.13

 Especially

1.12

 Absolutely

1.12

 Maybe

1.11

 Really

1.11

 Nothing

1.08

Activations Density 0.395%

sentences conveying emotional intensity or urgency

punctuated statements and exclamations in the text

Period at the end of short sentences.

No Comments

No Known Activations