INDEX

Explanations

mentions of awards, achievements, and recognitions received by individuals or organizations

oai_token-act-pair · gpt-3.5-turbo

references to awards and recognitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

UCT

-0.59

heid

-0.57

AppData

-0.57

adr

-0.57

ERA

-0.56

product

-0.56

pty

-0.55

WithNo

-0.53

needs

-0.52

van

-0.52

POSITIVE LOGITS

 include

2.24

 Include

1.67

 included

1.43

include

1.42

 includes

1.22

 includ

1.21

 consist

1.17

 abound

1.17

 vary

1.15

:-

1.14

Activations Density 0.478%

mentions of awards, achievements, and recognitions received by individuals or organizations

references to awards and recognitions

No Comments

No Known Activations