INDEX

Explanations

phrases related to enabling or empowering someone or something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "enable" 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

boy

-0.77

 Warcraft

-0.77

den

-0.67

kaya

-0.65

allo

-0.65

eal

-0.65

child

-0.63

ma

-0.63

ko

-0.62

 bite

-0.62

POSITIVE LOGITS

 guiActiveUn

0.96

 enable

0.90

 enabling

0.86

ments

0.86

 enables

0.85

MENTS

0.83

 confir

0.82

 enabled

0.80

iences

0.79

 misunder

0.77

Activations Density 0.013%

phrases related to enabling or empowering someone or something

instances of the word "enable" in various contexts

No Known Activations