INDEX

Explanations

phrases related to evaluation or judgment

oai_token-act-pair · gpt-3.5-turbo

instances of the pronoun "it" in various contexts

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

senal

-0.69

 ILCS

-0.67

 è£ıè¦ļéĨĴ

-0.66

 paran

-0.60

Wilson

-0.59

estern

-0.59

å½

-0.58

ãĥ¯ãĥ³

-0.57

èĢħ

-0.56

è¦ļéĨĴ

-0.56

POSITIVE LOGITS

ain

1.32

 nonetheless

1.23

 certainly

1.22

 nevertheless

1.22

 doesn

1.21

 wasn

1.19

isn

1.18

 does

1.15

 shouldn

1.14

 hasn

1.14

Activations Density 0.111%

phrases related to evaluation or judgment

instances of the pronoun "it" in various contexts

No Comments

No Known Activations