INDEX

Explanations

specific names or terms related to various contexts, such as individuals or organizations

oai_token-act-pair · gpt-3.5-turbo

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

 Maher

-0.79

 Letter

-0.68

 Daughter

-0.67

 TIME

-0.66

 Principle

-0.65

 Winn

-0.65

 Messenger

-0.63

 messenger

-0.63

 Notice

-0.63

tug

-0.63

POSITIVE LOGITS

eca

1.02

ic

1.01

ac

1.01

ico

1.00

isc

1.00

esc

0.99

ib

0.98

ec

0.98

ibus

0.94

icro

0.94

Activations Density 0.288%

specific names or terms related to various contexts, such as individuals or organizations

No Comments

No Known Activations