INDEX

Explanations

the word "suppose."

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "I suppose" or similar expressions indicating uncertainty or assumption

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

DOC

-0.79

wal

-0.73

assic

-0.70

atures

-0.68

ammy

-0.67

Tips

-0.65

haar

-0.63

ixt

-0.62

jab

-0.62

hor

-0.61

POSITIVE LOGITS

 suppose

0.71

elf

0.66

 Maggie

0.64

 phantom

0.63

 imagine

0.62

 assum

0.62

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

0.62

 Malfoy

0.61

ãĥ¼ãĥĨãĤ£

0.61

âĶĢâĶĢâĶĢâĶĢ

0.61

Activations Density 0.010%

the word "suppose."

instances of the phrase "I suppose" or similar expressions indicating uncertainty or assumption

No Comments

No Known Activations